© 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. 27251
    Prev
    Next
    INDEX
    Explanations

    criminals target or attack

    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
    å¾Ģå¤ĸ
    -0.09
    身为
    -0.09
    é¢ijéģĵ
    -0.09
    å¿¿
    -0.09
    ä¸İä¼Ĺ
    -0.09
    éĶĦ
    -0.09
    éģŃ
    -0.09
    OID
    -0.09
    kıl
    -0.09
    æĺ¯æĢİä¹Ī
    -0.09
    POSITIVE LOGITS
    adero
    0.10
    åĬ¿åĬĽ
    0.10
    èĤĨ
    0.10
    ç»ĻæĪij们
    0.10
    ä¼ģåĽ¾
    0.09
    å¦Ħ
    0.09
    åįĥæĸ¹çĻ¾è®¡
    0.09
    STA
    0.09
    enor
    0.09
     пÑĭÑĤа
    0.09
    Activations Density 0.095%

    No Known Activations