© 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. 45987
    Prev
    Next
    INDEX
    Explanations

    virtual virtual

    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
    èĭijå°ıåĮº
    -0.09
    ogan
    -0.09
    elv
    -0.08
    names
    -0.07
    emer
    -0.07
    .catch
    -0.07
     Bolton
    -0.07
    nock
    -0.07
    adden
    -0.07
    olley
    -0.07
    POSITIVE LOGITS
    çīĪçļĦ
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.07
    å¾®åŀĭ
    0.07
    ä»£æĽ¿
    0.07
     version
    0.07
    ìĭľíĶ¼
    0.07
     unofficial
    0.07
    é£İæĻ¯çº¿
    0.06
    ichtung
    0.06
    “
    0.06
    Activations Density 0.352%

    No Known Activations