© 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. 31205
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
    oss
    -0.07
    kip
    -0.06
     nap
    -0.06
    为æĮĩ导
    -0.06
     Nap
    -0.06
    ä¸ĵ
    -0.06
     Nature
    -0.06
    èĭį穹
    -0.06
    nap
    -0.06
    人
    -0.06
    POSITIVE LOGITS
    chers
    0.09
    mast
    0.08
    iszt
    0.08
     Mast
    0.07
    umfang
    0.07
    antas
    0.07
    è¼
    0.07
    ioned
    0.07
    äºĨä¸Ģçķª
    0.07
    chera
    0.07
    Activations Density 0.037%

    No Known Activations