© 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. 38655
    Prev
    Next
    INDEX
    Explanations

    more or much before quantity

    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
    quan
    -0.09
    ä¸įæĸŃ
    -0.08
    ä¸įæĸŃçļĦ
    -0.08
    åĽ´ç»ķ
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    gew
    -0.08
    çĽ¸äº²
    -0.07
    为æŃ¢
    -0.07
    ä¸įäºĨ
    -0.07
    éĿĵ
    -0.07
    POSITIVE LOGITS
    ĸī
    0.10
    èµŀåĬ©
    0.10
    çĽ¸å¹²
    0.10
    çļĦæĸ¹å¼ıæĿ¥
    0.09
    ritten
    0.09
     Noticed
    0.09
    à¸Ńà¸Ń
    0.09
    æĥħåł±ãĤĴ
    0.09
    çŀij
    0.09
    elpers
    0.09
    Activations Density 0.029%

    No Known Activations