© 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. 33552
    Prev
    Next
    INDEX
    Explanations

    criminal charges, fines, and victim restitution

    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
    强æľīåĬĽçļĦ
    -0.09
    顽
    -0.09
    ä¸İåıijå±ķ
    -0.09
    åıĮæīĭ
    -0.09
    æĬĦ
    -0.08
    æĹħ
    -0.08
    åĽĽèĤ¢
    -0.08
    æľĢåħĪè¿ĽçļĦ
    -0.08
    è¿IJèIJ¥ç®¡çIJĨ
    -0.08
    caps
    -0.08
    POSITIVE LOGITS
    æĬ¥æ¡Ī
    0.13
    å¿ĥçĸ¼
    0.10
    è´¢çī©
    0.10
    被害
    0.10
    æ²»
    0.10
    åķĨåºĹ
    0.10
    éĺ²çĽĹ
    0.09
    åįıåĬ©
    0.09
     crime
    0.09
    MBER
    0.09
    Activations Density 0.120%

    No Known Activations