© 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. 11275
    Prev
    Next
    INDEX
    Explanations

    motor

    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
     az
    -0.07
     순
    -0.06
    usion
    -0.06
    贤
    -0.06
     Thomson
    -0.06
    출
    -0.06
     synonymous
    -0.06
     BUT
    -0.06
     SV
    -0.06
    Sup
    -0.06
    POSITIVE LOGITS
     alter
    0.08
     harvesting
    0.07
     fires
    0.07
     vandal
    0.07
    (routes
    0.07
     milfs
    0.07
    Known
    0.07
    布置
    0.07
    _dirty
    0.07
    سأل
    0.07
    Activations Density 0.015%

    No Known Activations