© 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. 18281
    Prev
    Next
    INDEX
    Explanations

    wakefulness, alertness, sustain attention

    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
    èĻij
    -0.09
    å½ķ
    -0.09
    åįļçī©
    -0.09
    åı£å¾Ħ
    -0.09
    ople
    -0.09
    è¯ļ
    -0.09
    apiro
    -0.09
    çľĭä¸įè§ģ
    -0.09
    æłª
    -0.09
    /GL
    -0.09
    POSITIVE LOGITS
    æ¸ħéĨĴ
    0.13
    çĸ²åĬ³
    0.13
    éĨĴ
    0.12
     wake
    0.12
    åĢ¦
    0.11
    çŀĮ
    0.11
    æıIJ
    0.11
    åĭĥ
    0.11
     wakes
    0.10
    wake
    0.10
    Activations Density 0.065%

    No Known Activations