© 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. 35380
    Prev
    Next
    INDEX
    Explanations

    hurry, rush, haste

    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
    ãģĦãģ¡
    -0.09
    ä¸Ģå¥Ĺ
    -0.08
     Trot
    -0.08
    åĽ°æĥij
    -0.08
    èĻļåģĩ
    -0.08
    ä¸Ģ线
    -0.08
    é«ĺ度
    -0.08
    ardy
    -0.08
    æľº
    -0.08
    ä¸Ģåı£
    -0.08
    POSITIVE LOGITS
     chóng
    0.13
    NESS
    0.11
    ç¾İå¾·
    0.11
    èĪĽ
    0.10
    locks
    0.10
    ÑıÑī
    0.10
    é¹Ĭ
    0.09
    .cloudflare
    0.09
    ç¢
    0.09
    èµ·æĿ¥
    0.09
    Activations Density 0.006%

    No Known Activations