© 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. 62473
    Prev
    Next
    INDEX
    Explanations

    sleep/insomnia related terms

    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
     Mov
    -0.09
    è¿Ī
    -0.09
    衬
    -0.08
    .pic
    -0.08
     vent
    -0.08
    iff
    -0.08
    sealed
    -0.08
    å½ķçĶ¨
    -0.08
     Da
    -0.08
     movements
    -0.08
    POSITIVE LOGITS
    çĨ¬å¤ľ
    0.13
    å¤±çľł
    0.12
    寤
    0.12
    éĨĴäºĨ
    0.11
    æŁ´
    0.11
    åħ¥çĿ¡
    0.11
    çģ¯
    0.10
    åĬŁ
    0.10
    æĹ¥å¤ľ
    0.10
    æ¸ħéĨĴ
    0.10
    Activations Density 0.061%

    No Known Activations