© 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. 48641
    Prev
    Next
    INDEX
    Explanations

    company names and industries

    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¸ĢæĿ¡
    -0.10
    为ä¼ģä¸ļ
    -0.09
    å´
    -0.08
    峡谷
    -0.08
     goggles
    -0.08
     Hughes
    -0.08
     зай
    -0.08
    å¿ĥå¢ĥ
    -0.08
    .raise
    -0.07
    对éĿ¢
    -0.07
    POSITIVE LOGITS
    iset
    0.09
    æ¯ıä¸Ģ个人
    0.09
    çݰ代
    0.09
    çĪ±åĽ½ä¸»ä¹ī
    0.08
     Tib
    0.08
    çĹĪ
    0.08
    amenti
    0.08
    æ¯ıä¸Ģä½į
    0.08
    羣å®ŀçļĦ
    0.08
    å¿ħä¸įåı¯
    0.08
    Activations Density 0.339%

    No Known Activations