© 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. 55580
    Prev
    Next
    INDEX
    Explanations

    Wyoming

    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
    ivity
    -0.09
    Ļ
    -0.09
    ÑĨов
    -0.08
     trừ
    -0.08
    sch
    -0.08
    สาร
    -0.08
    ãĥ©ãĥ¼
    -0.08
    书记
    -0.08
    è¿ĻéĩĮ
    -0.08
    screens
    -0.08
    POSITIVE LOGITS
    rou
    0.10
    çľĩ
    0.09
    erval
    0.09
    unn
    0.09
    shire
    0.09
    ogle
    0.09
     Wyoming
    0.08
    è¢į
    0.08
    åįĩ
    0.08
    ality
    0.08
    Activations Density 0.012%

    No Known Activations