© 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. 6655
    Prev
    Next
    INDEX
    Explanations

    happy emotions

    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
    ç»ıæµİæĬĢæľ¯
    -0.10
    æ·±æĥħ
    -0.10
    鬲
    -0.09
    edList
    -0.09
    ç»ıåķĨ
    -0.09
    çķļ
    -0.09
    çŃīåĢĻ
    -0.09
     Ramp
    -0.09
    dre
    -0.09
    éĩįå·¥
    -0.09
    POSITIVE LOGITS
    满æĦı
    0.11
    иж
    0.10
    满æĦıçļĦ
    0.10
    æĪIJå°±æĦŁ
    0.10
     happy
    0.10
    å¼ĢæľĹ
    0.09
    oms
    0.09
    欢快
    0.09
    满满
    0.09
    ä¹IJ
    0.09
    Activations Density 0.061%

    No Known Activations