© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6324
    Prev
    Next
    INDEX
    Explanations

    share and sharing

    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
    衾
    -0.12
    ä¸įéĢļ
    -0.11
    é¼ĵèĪŀ
    -0.11
    æĻ®éĢļ人
    -0.11
    ailable
    -0.10
    å¸®ä½ł
    -0.10
    ç»·
    -0.10
    æĨĭ
    -0.10
    çļĦéŃħåĬĽ
    -0.09
    åĬ¿
    -0.09
    POSITIVE LOGITS
    IDA
    0.08
    ding
    0.08
    .LA
    0.08
    并ä¸į代表
    0.08
    ods
    0.07
    igel
    0.07
    allo
    0.07
    ä¸ĢåĪĨéĴ±
    0.07
     Locker
    0.07
    \$
    0.07
    Activations Density 0.002%

    No Known Activations