© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 637
    Prev
    Next
    INDEX
    Explanations

    police reports and incidents

    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
    Negative Logits
    зÑĥ
    -0.10
    éĺ»åĬĽ
    -0.10
    线æĿ¡
    -0.09
    说çļĦè¯Ŀ
    -0.09
    çļĦ好å¤Ħ
    -0.08
    åIJ¸çº³
    -0.08
    ä¹ı
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    ymoon
    -0.08
    piel
    -0.08
    POSITIVE LOGITS
    èѦæĸ¹
    0.13
     police
    0.12
    ä¸ĢåĪĻ
    0.11
    èŃ¦å¯Ł
    0.11
    æ¡Īä¾ĭ
    0.10
    æĸ°éĹ»
    0.10
     Police
    0.09
     incidents
    0.09
    åĪĿæŃ¥
    0.09
    æķħäºĭ
    0.09
    Activations Density 0.115%

    No Known Activations