© 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. 35497
    Prev
    Next
    INDEX
    Explanations

    training and physical exertion

    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
    èĢĥåľº
    -0.09
    ãģĦãģļãĤĮ
    -0.09
    æĻķ
    -0.09
    ä¸įæĪIJ
    -0.08
    éĺ»æĮ¡
    -0.08
     Barcl
    -0.08
    olvers
    -0.08
    _NE
    -0.08
    éĢŀ
    -0.08
    åĪĿ次
    -0.08
    POSITIVE LOGITS
    å°±æĺ¯ä¸ºäºĨ
    0.11
    åĽŀå½Ĵ
    0.10
    ä½ľæģ¯
    0.10
    奥æŀĹåĮ¹åħĭ
    0.09
    ç½ħ
    0.09
    涸
    0.09
    emax
    0.08
    庾
    0.08
    åıªä¸º
    0.08
    ä¸ĵéŨ
    0.08
    Activations Density 0.031%

    No Known Activations