© 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. 53643
    Prev
    Next
    INDEX
    Explanations

    preacher or inventor named

    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
    å¤įåı¤
    -0.09
    ç³ģ
    -0.09
    keit
    -0.09
    Fight
    -0.08
    è´²
    -0.08
    éĤ£ç§į
    -0.08
    串
    -0.08
    åĴ«
    -0.08
    ç»ıèIJ¥æ¨¡å¼ı
    -0.07
    éĹ®æĪij
    -0.07
    POSITIVE LOGITS
    没æľīåĬŀæ³ķ
    0.10
    çļĦæķħäºĭ
    0.10
    åľ¨å¸Ĥåľºä¸Ĭ
    0.10
    çŀĴ
    0.10
    ç»ıè¿ĩå¤ļå¹´
    0.09
    ä¾Ľå¤§å®¶
    0.09
    æĺ¯ä¸ºäºĨ
    0.09
    éĿŀåĩ¡
    0.09
     Legend
    0.09
    çĻ¼çı¾
    0.09
    Activations Density 0.102%

    No Known Activations