© 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. 58552
    Prev
    Next
    INDEX
    Explanations

    iaozi

    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
    æ¶Į
    -0.11
    ç«Ł
    -0.09
    afia
    -0.09
    ilon
    -0.09
    |min
    -0.08
    ä¸įåħģ许
    -0.08
    ç·Ĭ
    -0.08
    临港
    -0.08
    嬴
    -0.08
    oded
    -0.08
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.11
    ä½İ头
    0.10
    æĮł
    0.10
    å¾ĺå¾Ĭ
    0.10
    å¾Ĵ
    0.10
    ä¸ĢåĽ¢
    0.10
    å¾ĺ
    0.10
    åľĪåŃIJ
    0.09
    ç»ķ
    0.09
    çŀİ
    0.09
    Activations Density 0.072%

    No Known Activations