© 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. 34140
    Prev
    Next
    INDEX
    Explanations

    Iowa locations

    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
     Georgia
    -0.12
    Georgia
    -0.12
    æ¸Ŀ
    -0.11
     Atlanta
    -0.11
    绵éĺ³
    -0.11
    éķ¿å®ī
    -0.11
     Cyprus
    -0.11
    西å®īå¸Ĥ
    -0.11
    åįģåł°
    -0.11
    éĻķ西çľģ
    -0.10
    POSITIVE LOGITS
     Iowa
    0.14
     Sioux
    0.13
     Nebraska
    0.10
    hus
    0.10
     Leicester
    0.09
    éĺ¿æł¹å»·
    0.09
     Dakota
    0.09
    wor
    0.09
     Omaha
    0.09
     Fargo
    0.09
    Activations Density 0.149%

    No Known Activations