© 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. 47988
    Prev
    Next
    INDEX
    Explanations

    walking and movement

    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
    opher
    -0.10
    atern
    -0.10
    oyal
    -0.09
    yll
    -0.09
    оÑĤов
    -0.09
    éĻĦ
    -0.09
     phụ
    -0.08
    éĻĦåĬł
    -0.08
    ç²ķ
    -0.08
    èł¹
    -0.08
    POSITIVE LOGITS
    è½®å»ĵ
    0.09
    åįģæĿ¡
    0.09
    é¢IJ
    0.09
    è´ª
    0.08
    èĦļæŃ¥
    0.08
    lasses
    0.08
    éªĩ
    0.08
    æİĴæ¯Ĵ
    0.08
    ä¸įåĬ¨
    0.08
    akeup
    0.08
    Activations Density 0.019%

    No Known Activations