© 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. 11925
    Prev
    Next
    INDEX
    Explanations

    digital world. progress. click. first day

    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
    åģļèµ·
    -0.10
    åŁºéĩij份é¢Ŀ
    -0.09
    æĺ¯æĢİæł·
    -0.09
    家çĶ¨
    -0.09
    使ä¹ĭ
    -0.09
    ,{"
    -0.09
    æĺ¯å¦Ĥä½ķ
    -0.09
    è¿Ļæĺ¯æĪij
    -0.08
    ypi
    -0.08
    æ¦Ĥ
    -0.08
    POSITIVE LOGITS
    ngr
    0.08
    åĺĽ
    0.08
    ä¸įæĸŃçļĦ
    0.08
    é«¡
    0.08
    æĽ¿
    0.08
     Garr
    0.08
    çļĦè¿ĩç¨ĭ
    0.08
    æĪĸèĢħæĺ¯
    0.08
    æ¯ı个人éĥ½
    0.08
    踩
    0.07
    Activations Density 0.231%

    No Known Activations