© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    strong reactions and exclamations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĭĽåij¼
    -0.09
    åħ¬ç¤º
    -0.09
     fur
    -0.09
    AppBundle
    -0.09
    ðŁĵĺ
    -0.09
    .Peek
    -0.08
    è¾Ľè¾£
    -0.08
    éĩįçĤ¹é¡¹çĽ®
    -0.08
    å®īåħ¨æĦŁ
    -0.08
    æĹºçĽĽ
    -0.08
    POSITIVE LOGITS
    éĻ¤æѤ
    0.09
    ç¾İ人
    0.08
    inary
    0.08
    .datasource
    0.08
    æİīäºĨ
    0.08
     Aud
    0.08
    CV
    0.08
    ä¼ļè®©ä½ł
    0.08
    Council
    0.08
    aidu
    0.08
    Activations Density 0.019%

    No Known Activations