© 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. 47857
    Prev
    Next
    INDEX
    Explanations

    waking up early

    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
    æĹ©ä¸Ĭ
    -0.15
    æ¸ħæĻ¨
    -0.14
    éĨĴæĿ¥
    -0.13
    åįĬå¤ľ
    -0.13
     wake
    -0.13
    æĹ©æĻ¨
    -0.13
    åĶ¤éĨĴ
    -0.12
     wakeup
    -0.12
     Wake
    -0.12
     morning
    -0.11
    POSITIVE LOGITS
    çļĦå¿ĥçIJĨ
    0.10
    è¾ĵç»Ļ
    0.10
    ç»Ģ
    0.09
    çĬ¬
    0.09
    æĢĨ
    0.08
    ä¸ĵä¸ļæĬĢæľ¯
    0.08
    ÑĤки
    0.08
    viewer
    0.08
    ISIBLE
    0.08
     Opport
    0.08
    Activations Density 0.037%

    No Known Activations