© 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. 54035
    Prev
    Next
    INDEX
    Explanations

    IRS, tax, organizations, rules

    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
    åıijå±ķæ½ľåĬĽ
    -0.09
    è§ī
    -0.09
    æ°´æĻ¶
    -0.09
    ìĸ¼
    -0.08
    纽
    -0.08
    èĢģçĻ¾å§ĵ
    -0.08
    _demand
    -0.08
     Äijòi
    -0.08
     Iter
    -0.08
    emand
    -0.08
    POSITIVE LOGITS
    ç¨İåĬ¡æĢ»å±Ģ
    0.11
    IRT
    0.10
    IRS
    0.09
     IRS
    0.09
    æīĢå¾Ĺç¨İ
    0.09
    IRC
    0.09
    ç¨İåĬ¡
    0.09
    家éĥ½çŁ¥éģĵ
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
     Finder
    0.09
    Activations Density 0.112%

    No Known Activations