© 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. 31314
    Prev
    Next
    INDEX
    Explanations

    around time or date

    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
    æľ¬æĬ¥
    -0.09
    æĴĩ
    -0.09
    ê°ģ
    -0.09
    涯
    -0.08
    _ENDPOINT
    -0.08
    tti
    -0.08
    anness
    -0.08
     unborn
    -0.08
    æ¡ĥ
    -0.08
    ONT
    -0.08
    POSITIVE LOGITS
    -sized
    0.10
    å°±æĺ¯è¿Ļæł·
    0.09
    abouts
    0.09
    è¿Ļ个æŶåĢĻ
    0.09
    ä¸İæѤåIJĮæŶ
    0.09
    éĤ£ä¸ªæŶåĢĻ
    0.09
    äºİæĺ¯
    0.09
    以ä¸ĭåĩłä¸ª
    0.08
    亲å±ŀ
    0.08
    asl
    0.08
    Activations Density 0.021%

    No Known Activations