© 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. 58367
    Prev
    Next
    INDEX
    Explanations

    (c) )

    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
    èĦļè¸ıå®ŀ
    -0.07
    immel
    -0.07
    bach
    -0.07
    hack
    -0.06
    æĸ°èĢģ
    -0.06
    ekar
    -0.06
    ichel
    -0.06
    Selectors
    -0.06
    æ²³æ¹ĸ
    -0.06
    iali
    -0.06
    POSITIVE LOGITS
    none
    0.08
    ettings
    0.08
    None
    0.08
    rep
    0.08
     None
    0.08
    ètre
    0.08
    æľīæīĢæĢĿ
    0.07
    MB
    0.07
    ãģ©ãĤĮãĤĤ
    0.07
    ï¸ı
    0.07
    Activations Density 0.021%

    No Known Activations