© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    traffic violations and possession

    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
    åĨ¤
    -0.11
    ä¸Ńç¾İ
    -0.10
    å¾Ĺ天çĭ¬åİļ
    -0.09
    æ¤į
    -0.09
    æŃ£åĵģ
    -0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.09
    è¶ĬæĿ¥è¶Ĭ好
    -0.09
    èĺ¸
    -0.09
    é¹
    -0.09
    å¹³å®ī
    -0.09
    POSITIVE LOGITS
    æĵħ
    0.10
     manh
    0.08
    妨ç¢į
    0.08
    ç¿»
    0.08
    ove
    0.07
     drifting
    0.07
     catcher
    0.07
    anga
    0.07
     quán
    0.07
    对åŃ©åŃIJ
    0.07
    Activations Density 0.031%

    No Known Activations