© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 405
    Prev
    Next
    INDEX
    Explanations

    night and sleep related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     vulgar
    -0.27
    square
    -0.25
    æ¶ī足
    -0.23
    floating
    -0.23
    å¼ķçĶ¨
    -0.22
    éĨ
    -0.22
    æĵĤ
    -0.22
     Че
    -0.22
    éĵĨ
    -0.22
    Ether
    -0.22
    POSITIVE LOGITS
     nighttime
    0.40
     night
    0.38
     nightly
    0.38
     toddler
    0.37
     nights
    0.37
     ноÑĩ
    0.35
    çĿ¡çľł
    0.35
    -night
    0.35
    Night
    0.34
    å¤ľéĹ´
    0.34
    Activations Density 0.009%

    No Known Activations