© 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. 28048
    Prev
    Next
    INDEX
    Explanations

    police officers and sheriffs

    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
    èıĢ
    -0.11
    çŀ»
    -0.10
    礼æĭľ
    -0.10
    rael
    -0.09
    è¿ĩåħ³
    -0.09
    åĨ³
    -0.09
    åĽ¢ä½ĵ
    -0.09
     capitals
    -0.09
    å¸IJ
    -0.09
    äººæł¼
    -0.09
    POSITIVE LOGITS
    èŃ¦å¯Ł
    0.12
    èѦ
    0.11
    èѦåĬ¡
    0.11
    æ´¾åĩºæīĢ
    0.11
     officers
    0.11
    åĪijèѦ
    0.11
     police
    0.11
    æ°ijèѦ
    0.10
    交èѦ
    0.10
    åij¼
    0.09
    Activations Density 0.166%

    No Known Activations