© 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. 57979
    Prev
    Next
    INDEX
    Explanations

    must do

    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
    人å¿ĥ
    -0.10
    æĢ¥äºİ
    -0.09
    ä¹ħ
    -0.09
    æµģæ°´
    -0.09
    æ°ijå¿ĥ
    -0.09
     Outer
    -0.09
    peg
    -0.09
    è´ª
    -0.08
    -meta
    -0.08
    uen
    -0.08
    POSITIVE LOGITS
     chá»ĭu
    0.11
    æıIJä¾ĽæĽ´å¤ļ
    0.11
    æĭ¿åĩºæĿ¥
    0.11
    icted
    0.11
    è¦ģä¹Ī
    0.11
    æĭ¿åĩº
    0.10
    æī¿æĭħ责任
    0.10
    主åĬ¨
    0.10
    æī¿è®¤
    0.10
    нак
    0.10
    Activations Density 0.050%

    No Known Activations