© 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. 10742
    Prev
    Next
    INDEX
    Explanations

    food terms and organizations

    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
     istediÄŁi
    -0.09
    ä¸įå¤ļ
    -0.09
    ked
    -0.09
    .aw
    -0.09
    onald
    -0.09
     trá»Ŀi
    -0.08
    lain
    -0.08
    qua
    -0.08
    ä½İæĪIJæľ¬
    -0.08
    æĭīæĸ¯
    -0.08
    POSITIVE LOGITS
    æªĢ
    0.09
    æѤåĪ»
    0.09
    å§Ķæīĺ
    0.09
    为é¦ĸ
    0.09
    ä¸ĢåĽ¢
    0.09
    _checksum
    0.08
    è¾±
    0.08
    .fun
    0.08
    èĮ¹
    0.08
    桨
    0.08
    Activations Density 0.004%

    No Known Activations