© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 43892
    Prev
    Next
    INDEX
    Explanations

    wakefulness or day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uage
    -0.07
    udin
    -0.07
    ä½Ĩä¸įè¦ģ
    -0.07
    èij©
    -0.07
    ff
    -0.07
    antine
    -0.07
    æģ¼
    -0.07
    ktor
    -0.07
     Vern
    -0.07
    ffc
    -0.07
    POSITIVE LOGITS
    å°±ä¸įæĺ¯
    0.11
    æł¹æľ¬ä¸įæĺ¯
    0.09
    å·²ç»ıä¸įæĺ¯
    0.09
    éĥ½ä¸įæĺ¯
    0.08
    æĢİä¹Īä¼ļ
    0.08
    èĢĮä¸įæĺ¯
    0.08
     rather
    0.08
     Rather
    0.08
    æĢİä¹Īèĥ½
    0.08
     unless
    0.08
    Activations Density 0.046%

    No Known Activations