© 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. 17839
    Prev
    Next
    INDEX
    Explanations

    lawsuit and litigation contexts

    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
    Esc
    -0.09
    æĭħè´Ł
    -0.09
    æĪijçļĦå¿ĥ
    -0.09
    åİĨ代
    -0.09
    éĢĥèĦ±
    -0.09
     Esc
    -0.08
     Sandbox
    -0.08
     renov
    -0.08
    vas
    -0.08
    éĿĴå¹´
    -0.08
    POSITIVE LOGITS
    ç´¢èµĶ
    0.13
    èµĶåģ¿
    0.13
    工伤
    0.12
    计ç®ĹåĻ¨
    0.11
    交éĢļäºĭæķħ
    0.11
    æįŁå®³
    0.11
    è¡¥åģ¿
    0.10
    该æ¡Ī
    0.10
    åħ«åŃĹ
    0.10
    头æĿ¡
    0.10
    Activations Density 0.266%

    No Known Activations