© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23961
    Prev
    Next
    INDEX
    Explanations

    technical/legal/academic

    np_max-act · gemini-2.0-flash

    formal, abstract noun phrases in structured “X of Y” constructions—especially durations, categorizations, and other technical or legal list-like terms

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /********************************************************************************
    -0.07
     때문이다
    -0.07
    开来
    -0.07
    compression
    -0.07
    _FieldOffsetTable
    -0.07
    ;z
    -0.06
    ꦩ
    -0.06
    开奖
    -0.06
     exceptionally
    -0.06
    近年来
    -0.06
    POSITIVE LOGITS
     ElseIf
    0.08
     Shooting
    0.07
    rif
    0.07
     LIFE
    0.07
     Workout
    0.07
    elige
    0.06
     חופשי
    0.06
    owered
    0.06
    ﺦ
    0.06
     csrf
    0.06
    Activations Density 1.456%

    No Known Activations