© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9674
    Prev
    Next
    INDEX
    Explanations

    sleep and insomnia

    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
     Rehab
    -0.09
    æĻ¯èī²
    -0.09
    å°¸
    -0.09
    å¼Ģå°ģ
    -0.09
    æĬ¤
    -0.09
    ç¾°
    -0.08
    ERT
    -0.08
    æ®ĭå¿į
    -0.08
     ze
    -0.08
    éħ±æ²¹
    -0.08
    POSITIVE LOGITS
    å¤±çľł
    0.16
     sleep
    0.14
    çĿ¡çľł
    0.14
    åħ¥çĿ¡
    0.13
    çľł
    0.13
    å¤ľ
    0.12
    sleep
    0.12
    å¯IJ
    0.11
    çĿ¡
    0.11
     Sleep
    0.11
    Activations Density 0.037%

    No Known Activations