© 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. 45863
    Prev
    Next
    INDEX
    Explanations

    import numpy as np

    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
    ÛĮÙħÛĮ
    -0.09
    èŁĨ
    -0.09
    adb
    -0.08
    arken
    -0.08
    askell
    -0.08
    жек
    -0.07
    å¾ģå¾Ĺ
    -0.07
     Faro
    -0.07
    noon
    -0.07
    lei
    -0.07
    POSITIVE LOGITS
    heets
    0.07
    .array
    0.07
    imba
    0.06
    ä¹ĭéŃĤ
    0.06
    å¥ĸ
    0.06
    大夫
    0.06
    trx
    0.06
    å±±ä¸ĭ
    0.06
    ив
    0.06
     defaults
    0.06
    Activations Density 0.041%

    No Known Activations