© 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. 54768
    Prev
    Next
    INDEX
    Explanations

    Denver, Colorado courts

    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
    å·±
    -0.10
    alion
    -0.10
    ONS
    -0.09
     Gilbert
    -0.09
    æĬķæĶ¾
    -0.09
    æĸ
    -0.09
    ç¦ı建
    -0.09
    illis
    -0.09
    éģµå®Ī
    -0.09
    å©Ĩ
    -0.08
    POSITIVE LOGITS
     Colorado
    0.17
     Denver
    0.14
     Boulder
    0.13
    çī¦
    0.13
    Colorado
    0.13
    ä¸½æ±Ł
    0.12
    éĽªå±±
    0.11
    西èĹı
    0.11
    é«ĺåİŁ
    0.10
     Colo
    0.10
    Activations Density 0.161%

    No Known Activations