© 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. 61484
    Prev
    Next
    INDEX
    Explanations

    vast majority

    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
    深深
    -0.09
    åħħåĪĨèĤ¯å®ļ
    -0.09
    æĻ¯
    -0.09
     vision
    -0.08
    ((*
    -0.08
     кÑĢÑĭ
    -0.08
    æĻ®éģįåŃĺåľ¨
    -0.08
    æŀľçĦ¶
    -0.08
    archy
    -0.08
    éĢĤæŶ
    -0.08
    POSITIVE LOGITS
    uments
    0.11
    ulk
    0.11
    迹
    0.10
    è·¡
    0.10
    ouple
    0.09
    ä¸ĢéĹª
    0.09
    tero
    0.09
    pire
    0.09
    hort
    0.09
     Bernardino
    0.09
    Activations Density 0.013%

    No Known Activations