© 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. 4554
    Prev
    Next
    INDEX
    Explanations

    python scripts

    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
     Rach
    -0.09
    å¾Īåĸľæ¬¢
    -0.09
    ç»Ŀä¸į
    -0.09
    è²Įä¼¼
    -0.09
    .pat
    -0.09
    åľ¨å¤ĸ
    -0.09
    ç»Ŀ
    -0.08
    orth
    -0.08
    tracer
    -0.08
    ushi
    -0.08
    POSITIVE LOGITS
    æıIJä¾ĽæĽ´å¤ļ
    0.11
    åIJĮæľŁ
    0.11
    è¦ĨçĽĸéĿ¢
    0.10
    oom
    0.10
    ä¾ĽéľĢ
    0.10
    è¦ĨçĽĸ
    0.09
    è°ª
    0.09
    åºķæ°Ķ
    0.09
    ç¼ĵåĨ²
    0.09
    èĻij
    0.09
    Activations Density 0.352%

    No Known Activations