© 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. 41167
    Prev
    Next
    INDEX
    Explanations

    NAME: or Title:

    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
    ovin
    -0.08
     Tomorrow
    -0.07
    严
    -0.07
    é©°
    -0.07
    ugg
    -0.07
    åݦ
    -0.06
    Ùħرة
    -0.06
    çİ°
    -0.06
    æĺİæĹ¥
    -0.06
    fov
    -0.06
    POSITIVE LOGITS
    åıĭæĥħæıIJ示
    0.08
     sideline
    0.08
    /questions
    0.08
    otel
    0.07
    abria
    0.07
     sidelines
    0.07
    ixin
    0.07
    ille
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    Rect
    0.07
    Activations Density 0.001%

    No Known Activations