© 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. 35220
    Prev
    Next
    INDEX
    Explanations

    part of GCC. free software

    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
    æĹłæĦı
    -0.10
    edor
    -0.09
     lev
    -0.09
    éģ¨
    -0.09
    edin
    -0.09
    .addView
    -0.09
    è¿Ļ家
    -0.09
    æĮ¨
    -0.09
    mdi
    -0.08
    ä¹Łè®¸æĺ¯
    -0.08
    POSITIVE LOGITS
    _HOOK
    0.10
    滥
    0.10
     Emacs
    0.09
    .gnu
    0.09
    æ»ŀ
    0.09
    .tex
    0.09
    OMPI
    0.08
    åĵī
    0.08
    æįı
    0.08
    ĮĢ
    0.08
    Activations Density 0.265%

    No Known Activations