© 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. 26521
    Prev
    Next
    INDEX
    Explanations

    created / established organizations

    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¸įä¸Ĭ
    -0.09
    /manual
    -0.08
    èİ·æĤī
    -0.08
    ÃľN
    -0.08
    onom
    -0.08
    PTS
    -0.08
    elist
    -0.08
    åIJŃ
    -0.08
    wap
    -0.07
    ICY
    -0.07
    POSITIVE LOGITS
    è¿IJä½ľ
    0.19
    æĪIJç«ĭ
    0.18
    æĪIJç«ĭäºİ
    0.17
    è¿IJ转
    0.17
    æĪIJç«ĭ以æĿ¥
    0.15
    ä¸ĵéŨ
    0.14
    æĪIJç«ĭäºĨ
    0.13
    解æķ£
    0.13
    æıŃçīĮ
    0.12
    设ç«ĭ
    0.12
    Activations Density 0.203%

    No Known Activations