© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53205
    Prev
    Next
    INDEX
    Explanations

    Anderson surnames and place names

    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
    ãģĤãģ¾ãĤĬ
    -0.10
    odos
    -0.09
    è¡·
    -0.09
    å·´å·´
    -0.09
    iled
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    /her
    -0.09
    ÑĢÑĥд
    -0.09
    年人
    -0.09
    arend
    -0.08
    POSITIVE LOGITS
    oret
    0.10
    /OR
    0.09
    ä¼ļåIJĮ
    0.09
    hu
    0.09
    burg
    0.09
    ering
    0.09
    rade
    0.09
    дей
    0.09
    Ùħ
    0.09
    esor
    0.09
    Activations Density 0.011%

    No Known Activations