© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 6533
    Prev
    Next
    INDEX
    Explanations

    combat/war

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    רכב
    -0.07
     יעקב
    -0.07
     ../../
    -0.07
    agens
    -0.07
    較
    -0.07
    (klass
    -0.07
    娼
    -0.07
    ◭
    -0.07
    _coeffs
    -0.07
    .ticket
    -0.07
    POSITIVE LOGITS
     العلي
    0.07
    Friendly
    0.07
     é
    0.06
    用户
    0.06
     dari
    0.06
    Hy
    0.06
    过滤
    0.06
    .xpath
    0.06
    �
    0.06
    得到
    0.06
    Activations Density 0.081%

    No Known Activations