© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8955
    Prev
    Next
    INDEX
    Explanations

    radical and hydroxyl (OH)

    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
    æŃ¥æŃ¥é«ĺ
    -0.07
    egger
    -0.07
    åºķä¸ĭçļĦ
    -0.07
     vot
    -0.06
    ÑĦеÑĢен
    -0.06
    elmi
    -0.06
     candidature
    -0.06
    榨
    -0.06
    áĥļáĥĿáĥij
    -0.06
    icago
    -0.06
    POSITIVE LOGITS
    西æŀĹ
    0.09
    èµ·æīĭ
    0.08
    inston
    0.08
    -init
    0.08
    Reusable
    0.08
    วà¸ĩ
    0.08
    á»ijc
    0.08
    ustos
    0.08
     generated
    0.08
    _INITIALIZ
    0.08
    Activations Density 0.011%

    No Known Activations