© 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. 608
    Prev
    Next
    INDEX
    Explanations

    allergies and skin issues

    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
    温馨
    -0.11
    红æĹĹ
    -0.10
    å°¸
    -0.10
    ç¬ij声
    -0.09
    æĻļæľŁ
    -0.09
    pery
    -0.09
    ç«ĭ
    -0.09
    acie
    -0.09
    伤å¿ĥ
    -0.09
    eger
    -0.08
    POSITIVE LOGITS
    ä½ĵè´¨
    0.11
    ÑĤÑĥÑĢ
    0.10
    è¿ĩæķı
    0.10
     flare
    0.10
    èĦ¾èĥĥ
    0.10
    é¥®é£Ł
    0.09
     constitutional
    0.09
    æķıæĦŁ
    0.09
    åĵij
    0.09
    é¨
    0.09
    Activations Density 0.041%

    No Known Activations