© 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. 29934
    Prev
    Next
    INDEX
    Explanations

    names and usernames

    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
    è¿ĻåĿĹ
    -0.10
    ÑĦон
    -0.09
    çłĶ究åijĺ
    -0.09
    ãĤĴåıĸãĤĬ
    -0.09
    è°
    -0.09
    å¸ĮæľĽå¤§å®¶
    -0.09
    èij³
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.08
    INGTON
    -0.08
    aland
    -0.08
    POSITIVE LOGITS
    nore
    0.08
    çļĦæľĭåıĭ
    0.08
    æĮīæŶ
    0.08
    ä¸Ģ家人
    0.08
    èªī
    0.08
    ä¸ĸ家
    0.08
    ä¸Ģ家
    0.08
    æŁ¥çľĭæĽ´å¤ļ
    0.07
    è´µ
    0.07
    æŃ¥æŃ¥
    0.07
    Activations Density 0.032%

    No Known Activations