© 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. 16549
    Prev
    Next
    INDEX
    Explanations

    drama film

    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
    itaire
    -0.11
    itan
    -0.10
    uu
    -0.09
    TING
    -0.08
    amarin
    -0.08
    erb
    -0.08
    iore
    -0.08
    åij¨å¹´
    -0.08
    ãĥ¥
    -0.08
    ivid
    -0.08
    POSITIVE LOGITS
    matic
    0.12
    atically
    0.09
    rets
    0.09
    mando
    0.08
    ous
    0.08
    antt
    0.08
    IED
    0.08
    æ»ĵ
    0.08
    ศาส
    0.08
     nghiá»ĩp
    0.08
    Activations Density 0.007%

    No Known Activations