© 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. 56441
    Prev
    Next
    INDEX
    Explanations

    sweat related words

    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
    urate
    -0.09
     же
    -0.09
    æ´ŀ
    -0.08
    éĽ¢ãĤĮ
    -0.08
     PRES
    -0.08
    纯粹
    -0.08
    ×ķ×Ļ
    -0.08
    åĴ¥
    -0.08
    ä¸Ģæłĭ
    -0.08
    éĻIJãĤĬ
    -0.08
    POSITIVE LOGITS
    è¡·
    0.13
    æģĥ
    0.10
    esh
    0.09
    edly
    0.09
    rooms
    0.08
    LESS
    0.08
    æ¸į
    0.08
    ç¥ĸçĪ¶
    0.08
    staking
    0.08
    áĢĩ
    0.08
    Activations Density 0.003%

    No Known Activations