© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60553
    Prev
    Next
    INDEX
    Explanations

    follow-up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ahas
    -0.10
    éħIJ
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    ä¸ĢæĹı
    -0.09
    iances
    -0.09
    estate
    -0.09
    afort
    -0.09
    åīįåĪĹ
    -0.09
    æĻļæĬ¥
    -0.09
    ä¸Ģéĥ¨
    -0.09
    POSITIVE LOGITS
     Sext
    0.09
    OrCreate
    0.09
    èĻļ
    0.09
    hoe
    0.08
    .getAs
    0.08
    zzo
    0.08
    æ¿Ģ
    0.08
     virtual
    0.08
    å²Ľå±¿
    0.08
    virtual
    0.08
    Activations Density 0.016%

    No Known Activations