© 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. 56510
    Prev
    Next
    INDEX
    Explanations

    known to consist

    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
    æ¼Ķ
    -0.11
    骤
    -0.11
    åĥĸ
    -0.09
    ä¸įåłª
    -0.09
    侧éĿ¢
    -0.09
    noop
    -0.09
    åĽ´æ£ĭ
    -0.09
    inputs
    -0.09
    _learn
    -0.09
    çªł
    -0.08
    POSITIVE LOGITS
    çŀ¥
    0.10
     tends
    0.09
    æľīæŶåĢĻ
    0.09
    èŀºæĹĭ
    0.08
    æľīæŶ
    0.08
    artner
    0.08
     sometimes
    0.08
     иногда
    0.08
    ç¥ļ
    0.08
    æ¸İ
    0.08
    Activations Density 0.057%

    No Known Activations