© 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. 18924
    Prev
    Next
    INDEX
    Explanations

    quantity or availability

    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
    ä¸įåı¯éģ¿åħį
    -0.11
     нев
    -0.09
     Twe
    -0.09
    æ¡ĮéĿ¢
    -0.09
    ä¸įåı¯
    -0.09
    æĹłåı¯
    -0.09
    åıªä¸įè¿ĩ
    -0.09
    æĪijåıªæĺ¯
    -0.09
    )<<
    -0.09
    ãĤ«ãĥ¼
    -0.09
    POSITIVE LOGITS
     Rings
    0.09
     plenty
    0.09
     ring
    0.08
    éĻµ
    0.08
    ãģ¨ãģįãģ¯
    0.08
     rings
    0.08
    åĢĴæĺ¯
    0.08
    lingen
    0.07
    èī²å½©
    0.07
    ring
    0.07
    Activations Density 0.021%

    No Known Activations