Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 49823
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    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
    知
    -0.07
     hors
    -0.07
    科尔
    -0.07
    <$
    -0.06
     countered
    -0.06
     содержит
    -0.06
     COS
    -0.06
    千方
    -0.06
     Curl
    -0.06
    _capability
    -0.06
    POSITIVE LOGITS
     policym
    0.07
    ella
    0.07
    จำ
    0.07
    企业发展
    0.07
     bug
    0.06
    يب
    0.06
    良
    0.06
    .")
    ↵
    0.06
    lime
    0.06
    ">↵
    0.06
    Activations Density 0.007%

    No Known Activations