© 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. 53575
    Prev
    Next
    INDEX
    Explanations

    group of

    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
    ä¸Ģ个èģĮä¸ļ
    -0.11
    è¿ĻæĿ¡è·¯
    -0.10
    ilan
    -0.10
    éĥ¨åĪĨåľ°åĮº
    -0.09
    éĥ½æĥ³
    -0.09
    è¿Ļæĺ¯ä¸Ģ个
    -0.09
    ä¸Ģ个
    -0.09
    æķ´ä¸ªäºº
    -0.08
    ç§įç§į
    -0.08
     numerous
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.16
    omanip
    0.10
    [group
    0.10
     dÆ°
    0.09
    пл
    0.09
     ÑĢанее
    0.09
    家ä¼Ļ
    0.09
     Ñĩеловека
    0.09
    å¼ĤæĢ§
    0.09
    被æĬĵ
    0.09
    Activations Density 0.059%

    No Known Activations