© 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. 61385
    Prev
    Next
    INDEX
    Explanations

    vehicles and transportation

    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
    éļıæīĭ
    -0.12
    è´£ç¼ĸ
    -0.10
    责任åĪ¶
    -0.10
    /license
    -0.09
    ç²®
    -0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.09
    æīĭ表
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    éªı
    -0.09
    æĦıæĢĿæĺ¯
    -0.09
    POSITIVE LOGITS
    ucha
    0.09
    AGR
    0.08
    à°³
    0.08
     conversions
    0.08
     Barg
    0.08
    ç¦ıç¥ī
    0.08
    Become
    0.08
    lude
    0.08
    侧éĿ¢
    0.08
    Ordinal
    0.07
    Activations Density 0.009%

    No Known Activations