© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    U.S. states and Canadian provinces

    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
    èĭıå·ŀå¸Ĥ
    -0.15
    åįĹ京å¸Ĥ
    -0.14
    èĭıå·ŀ
    -0.12
    Atlanta
    -0.11
    æĹłéĶ¡
    -0.11
    常å·ŀ
    -0.11
    éĩijéĻµ
    -0.11
    æ±Łèĭıçľģ
    -0.10
    溧
    -0.10
    æ·±åľ³å¸Ĥ
    -0.10
    POSITIVE LOGITS
    æ´®
    0.17
     Saskatchewan
    0.16
     Fargo
    0.14
     Dakota
    0.13
    å°ķ
    0.13
     Montana
    0.13
     Sask
    0.12
     Sioux
    0.12
     Manitoba
    0.12
     Winnipeg
    0.12
    Activations Density 0.221%

    No Known Activations