© 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. 26438
    Prev
    Next
    INDEX
    Explanations

    git pull client

    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
    eced
    -0.08
    ä»ħä¾Ľ
    -0.08
    hey
    -0.07
     ×ŀ×ĺ
    -0.07
    財
    -0.07
    rz
    -0.07
    um
    -0.07
    ä¸Ģå¼ı
    -0.07
    orz
    -0.07
     umo
    -0.07
    POSITIVE LOGITS
    é£İ度
    0.07
    emes
    0.07
    fér
    0.07
    ink
    0.07
    以太
    0.07
    éªı
    0.06
    inks
    0.06
    inker
    0.06
    å¾Ĺä¸į
    0.06
    人ä¹ĭ
    0.06
    Activations Density 0.007%

    No Known Activations