© 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. 19-RESID-POST-AA
    6. 109650
    Prev
    Next
    INDEX
    Explanations

    Mixed languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    꼐
    -0.07
     coats
    -0.07
    具有一定
    -0.07
    .EOF
    -0.07
     QColor
    -0.07
    日报
    -0.07
    _money
    -0.07
    コミュニケーション
    -0.07
    ziej
    -0.06
     acceso
    -0.06
    POSITIVE LOGITS
    ❈
    0.07
    .merge
    0.07
     使用
    0.07
     mines
    0.07
    続けて
    0.07
    curity
    0.07
    sw
    0.06
     Try
    0.06
    ♓
    0.06
    _flush
    0.06
    Activations Density 0.119%

    No Known Activations