© 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. 19-RESID-POST-AA
    11. 62459
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific texts

    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
    Negative Logits
     mắt
    -0.07
    Normally
    -0.07
    年人
    -0.06
    Ỳ
    -0.06
    忘れ
    -0.06
     precaution
    -0.06
     חו
    -0.06
    override
    -0.06
    lok
    -0.06
     crianças
    -0.06
    POSITIVE LOGITS
    起重机
    0.07
     mentioning
    0.07
    _login
    0.07
    .setFill
    0.07
     Điện
    0.07
     primitives
    0.07
    ген
    0.07
    topic
    0.06
    水流
    0.06
     eighteen
    0.06
    Activations Density 0.040%

    No Known Activations