© 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. 6416
    Prev
    Next
    INDEX
    Explanations

    cold and respiratory infections

    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
    å±į
    -0.09
    èĻ
    -0.09
    çļĦåİĭåĬĽ
    -0.09
    çĿģ
    -0.09
    å°¸
    -0.09
    èł
    -0.09
    æģIJ
    -0.09
    æݨ
    -0.09
    cord
    -0.08
    ç¼Ĩ
    -0.08
    POSITIVE LOGITS
    æĦŁåĨĴ
    0.17
    æµģæĦŁ
    0.13
     illness
    0.11
    åĴ³åĹ½
    0.11
    é¼»
    0.10
    åŃ£èĬĤ
    0.10
    åĴ³
    0.10
    æĺ¥è¿IJ
    0.10
    åij¼åIJ¸éģĵ
    0.09
    ascade
    0.09
    Activations Density 0.082%

    No Known Activations