© 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. 26484
    Prev
    Next
    INDEX
    Explanations

    BEGIN followed by DH or RSA or LICENSE

    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
    undy
    -0.11
    çļĦ缮çļĦ
    -0.09
    çīºçī²
    -0.09
    第ä¸ī代
    -0.09
     sake
    -0.09
    åIJĦ个æĸ¹éĿ¢
    -0.09
     Baths
    -0.09
    缮çļĦåľ¨äºİ
    -0.09
    lices
    -0.08
    lei
    -0.08
    POSITIVE LOGITS
    æĿ¥åĪ°äºĨ
    0.10
    é²ĭ
    0.09
    è¦ģ说
    0.09
    è¿ĻéĩĮæľī
    0.09
     Zw
    0.08
    iew
    0.08
    å°ı康
    0.08
    antis
    0.08
    产åIJİ
    0.08
    /doc
    0.08
    Activations Density 0.037%

    No Known Activations