© 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. 62544
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    æĺ¨æĹ¥
    -0.10
    çIJĨå·¥
    -0.10
    羣æĺ¯
    -0.09
    åĩłå¹´åīį
    -0.09
    æĺ¨å¤©
    -0.09
    çİ°éĺ¶æ®µ
    -0.09
    å°±æѤ
    -0.09
    MARY
    -0.08
    è¾ĵ
    -0.08
    Ticker
    -0.08
    POSITIVE LOGITS
    å®īæİĴ
    0.10
    åı¦è¡Į
    0.10
     yapılacak
    0.09
    å±ĬæŶ
    0.09
     scheduled
    0.09
    cheduled
    0.09
    å°Ĩäºİ
    0.08
     schedule
    0.08
    (schedule
    0.08
    ä¸ĭ次
    0.08
    Activations Density 0.019%

    No Known Activations