© 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. 50230
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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
    iers
    -0.12
    arella
    -0.09
    ord
    -0.09
    çľĭä½ł
    -0.09
    è¯Ŀ说
    -0.08
    rock
    -0.08
     Kitt
    -0.08
    -yard
    -0.08
    kus
    -0.08
    ä»ĸæĽ¾
    -0.08
    POSITIVE LOGITS
    ä¾Ĩèĩª
    0.10
    _CID
    0.10
    æĿ¥èĩª
    0.09
    礼æĭľ
    0.09
    ìĤ¬íķŃ
    0.09
    æĿ¥èĩªäºİ
    0.09
    FileVersion
    0.09
     dotyczÄħce
    0.09
    haps
    0.09
    ëį°
    0.09
    Activations Density 0.027%

    No Known Activations