© 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. 33211
    Prev
    Next
    INDEX
    Explanations

    seeking explanation or reason

    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
     blame
    -0.09
    积æŀģ
    -0.09
     обÑĭ
    -0.08
    çijķ
    -0.08
    讯
    -0.08
    åĿı
    -0.08
     szko
    -0.08
    èĥ½åĬĽåĴĮ
    -0.08
    æ¦Ĥæĭ¬
    -0.08
    详ç»Ĩä»ĭç»į
    -0.08
    POSITIVE LOGITS
    éļ¾æĢª
    0.12
    åİĨæĿ¥
    0.10
    为ä»Ģä¹Ī
    0.09
    为ä»Ģä¹Īä¸į
    0.09
    abet
    0.09
    为åķ¥
    0.09
    为ä½ķ
    0.09
    çĤºä»Ģ麼
    0.08
    hatt
    0.08
    éļIJèĶ½
    0.08
    Activations Density 0.043%

    No Known Activations