© 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. 18377
    Prev
    Next
    INDEX
    Explanations

    performing actions or tasks

    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
    æ¼Ķä¹ł
    -0.09
    åľ¨åħ¶
    -0.09
    å¾Ĺå¾Ī好
    -0.09
     exc
    -0.09
    çļĦåĪ°æĿ¥
    -0.09
    éŀį
    -0.09
    太é«ĺ
    -0.09
    ç»ıæŁ¥
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    æĵ¦
    -0.08
    POSITIVE LOGITS
    /testing
    0.10
    åĪĿ次
    0.09
    第ä¸ī次
    0.08
    大åѦæ¯ķä¸ļ
    0.08
    ании
    0.08
    æ»´
    0.08
    .hasOwnProperty
    0.08
    eneg
    0.08
     ÑģÑĤоим
    0.08
     Weaver
    0.08
    Activations Density 0.073%

    No Known Activations