© 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. 57155
    Prev
    Next
    INDEX
    Explanations

    view PDF or open file

    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
    帮
    -0.09
    幫
    -0.09
    积èĵĦ
    -0.09
    亿ä¸ĩ
    -0.09
    âķ
    -0.09
    å¥ijæľº
    -0.09
    بة
    -0.08
    bull
    -0.08
    æŀ¢çº½
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    POSITIVE LOGITS
    yre
    0.10
    æµıè§ĪåĻ¨
    0.10
     browsers
    0.10
     browser
    0.09
    clipse
    0.09
    æµıè§Ī
    0.09
    ãĥĸãĥ©
    0.09
     preview
    0.09
    preview
    0.09
    .chrome
    0.09
    Activations Density 0.125%

    No Known Activations