© 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. 40575
    Prev
    Next
    INDEX
    Explanations

    time in H:M:S format

    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
    orsche
    -0.08
    ëķħ
    -0.08
    äºĨä¸ĭæĿ¥
    -0.08
    ä¸ĭæĿ¥äºĨ
    -0.07
    ä¸ĭæĿ¥
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ẻ
    -0.07
    غار
    -0.07
    гÑĢад
    -0.07
    Verifier
    -0.07
    POSITIVE LOGITS
     UTC
    0.08
    UTC
    0.07
     GMT
    0.07
    iasi
    0.07
     thro
    0.07
    æ¸Ń
    0.07
    GMT
    0.06
     midnight
    0.06
     hour
    0.06
     Sour
    0.06
    Activations Density 0.190%

    No Known Activations