© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19742
    Prev
    Next
    INDEX
    Explanations

    legal challenge or appeal

    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
    anus
    -0.10
    髯
    -0.09
    laps
    -0.09
    ä¸į对
    -0.09
    çݺ
    -0.09
    åįĹåĮĹ
    -0.09
    éĵ§
    -0.09
    .Priority
    -0.09
    ä»ĸä¹Ł
    -0.09
    è¯ģ
    -0.09
    POSITIVE LOGITS
    ä¸įæľį
    0.11
    åıijåĬ¨
    0.10
    æīĵèµ¢
    0.10
    å¤įæŁ¥
    0.09
    æ¦Ĩ
    0.09
    大æĪĺ
    0.09
    ä¸įåģľ
    0.08
     Townsend
    0.08
     post
    0.08
     challenge
    0.08
    Activations Density 0.146%

    No Known Activations