© 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. 62331
    Prev
    Next
    INDEX
    Explanations

    eyelashes, hyaluronate, hydrophobic, face mask, touch panel

    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
    abal
    -0.08
     ëĵł
    -0.07
     ëŀĺ
    -0.07
    éķIJ
    -0.07
    urr
    -0.07
    onat
    -0.06
    ibal
    -0.06
    è°
    -0.06
    走好
    -0.06
    æīĭæľºéĺħ读
    -0.06
    POSITIVE LOGITS
    assistant
    0.07
    zl
    0.07
    ÌĢ
    0.07
    æ±Ĥæĺ¯
    0.06
     Hav
    0.06
    ksen
    0.06
    joj
    0.06
    cb
    0.06
    HAV
    0.06
    åİļå¾·
    0.06
    Activations Density 1.249%

    No Known Activations