© 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. 26728
    Prev
    Next
    INDEX
    Explanations

    gynecology, urology

    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
    inel
    -0.10
    ä¼ļ使
    -0.09
    对ä¼ģä¸ļ
    -0.09
    é¥Ń
    -0.09
    jure
    -0.09
    çĶµåİĤ
    -0.08
    .tap
    -0.08
    çŃĴ
    -0.08
    è¾ĥ好çļĦ
    -0.08
    _GAP
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁ
    0.12
    éĥ¨ä¸»ä»»
    0.11
    é¢ĨåŁŁçļĦ
    0.09
    éĥ¨
    0.09
    éłĺåŁŁ
    0.09
     nghiá»ĩp
    0.09
    çĥŁèĬ±
    0.08
    æĿĤ
    0.08
    åĸģ
    0.08
    æľ¯
    0.08
    Activations Density 0.167%

    No Known Activations