© 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. 58236
    Prev
    Next
    INDEX
    Explanations

    biophotonics, brain, neurons, mental level

    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
    为ä¹ĭ
    -0.11
    æĪ®
    -0.10
    ç»Ī身
    -0.10
    expert
    -0.09
    á¹ĵ
    -0.09
    åĢĺ
    -0.09
    çıª
    -0.09
    .gca
    -0.09
     Gilles
    -0.09
    nil
    -0.09
    POSITIVE LOGITS
    ç¥
    0.10
    ä¸Ĭä¼ł
    0.09
     prod
    0.08
    инÑĭ
    0.08
    èĤ¡
    0.08
    .operator
    0.08
    èĸı
    0.08
    主管
    0.08
    åĵ¼
    0.08
    _pkg
    0.08
    Activations Density 0.174%

    No Known Activations