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. 11-RESID-POST-AA
    6. 92312
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REATED
    -0.07
     לבטל
    -0.07
    edly
    -0.07
     sounded
    -0.06
    עמוד
    -0.06
    uncia
    -0.06
    itur
    -0.06
    another
    -0.06
    㮾
    -0.06
    未来
    -0.06
    POSITIVE LOGITS
     chuyện
    0.08
    分校
    0.07
     pornstar
    0.07
    二线城市
    0.07
    农村
    0.07
     Cache
    0.07
    .done
    0.07
    _office
    0.07
    _INSTANCE
    0.07
     reachable
    0.07
    Activations Density 0.008%

    No Known Activations