© 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. 55516
    Prev
    Next
    INDEX
    Explanations

    criminal charges and legal proceedings

    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
     Lonely
    -0.09
    Sir
    -0.08
    èĥĥåı£
    -0.08
    èĩªä¿¡
    -0.08
    è¯ľ
    -0.08
     DISCLAIMS
    -0.08
    è¿Ļ个游æĪı
    -0.08
    åĬŀ好
    -0.08
     hip
    -0.07
     crumbs
    -0.07
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.11
    穹
    0.09
    对她
    0.09
    ä¸ĭè¾¾
    0.09
    ç«ĭåį³
    0.09
    æľ¬æľĪ
    0.09
    éĿ¢éĥ¨
    0.09
    æİĩ
    0.09
    å®ŀéªĮ室
    0.08
    PCR
    0.08
    Activations Density 0.114%

    No Known Activations