© 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. 102912
    Prev
    Next
    INDEX
    Explanations

    Formal language

    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
     sparked
    -0.07
    큭
    -0.07
    ニー
    -0.07
     rode
    -0.07
     Forge
    -0.07
    erialized
    -0.07
     lié
    -0.07
     cougar
    -0.07
     forged
    -0.06
     Suppress
    -0.06
    POSITIVE LOGITS
    спор
    0.07
    海峡
    0.07
     Pont
    0.07
    help
    0.07
    公
    0.07
    лав
    0.07
    ђ
    0.07
    orth
    0.07
    张家界
    0.06
    ọ
    0.06
    Activations Density 0.018%

    No Known Activations