© 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. 49576
    Prev
    Next
    INDEX
    Explanations

    on the surface of

    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
     Brit
    -0.09
    å¢Ł
    -0.09
    帮æĪij
    -0.09
    å·¥ä½ľç«Ļ
    -0.08
    pit
    -0.08
    ä¸ī级
    -0.08
    æµģæ°´
    -0.08
    ç¡®
    -0.08
     Hub
    -0.08
    å°ıåºĹ
    -0.08
    POSITIVE LOGITS
    侧éĿ¢
    0.15
    èĥĮéĿ¢
    0.14
     underside
    0.11
    åģ´
    0.11
    çļĦä¸ĢéĿ¢
    0.11
    侧
    0.11
    éĿ¢åIJij
    0.11
    å¤ĸéĥ¨
    0.10
    表éĿ¢
    0.10
    éĿ¢ä¸Ĭ
    0.10
    Activations Density 0.184%

    No Known Activations