© 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. 57340
    Prev
    Next
    INDEX
    Explanations

    gamcho, caravel, pique

    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
    çļĦ人
    -0.09
    çªĹå¤ĸ
    -0.09
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    å¸ĤæķĻèĤ²
    -0.08
    åĪĨ解
    -0.08
    çļĦæ¯į亲
    -0.08
    è°³
    -0.08
    ä¸Ģ代
    -0.08
    ÑĪе
    -0.08
    moduleId
    -0.08
    POSITIVE LOGITS
    缸éĢļ
    0.09
    æĦıåij³
    0.09
     Fut
    0.09
    åľ¨æĪijåĽ½
    0.09
    è¿Ļ个è¯į
    0.08
    鬼
    0.08
    åįĪ
    0.08
    reten
    0.08
     ij
    0.08
    Translator
    0.07
    Activations Density 0.116%

    No Known Activations