© 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. 41415
    Prev
    Next
    INDEX
    Explanations

    Starts with "Articles" or "This"

    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
     pose
    -0.07
    ãĤīãģļ
    -0.07
     overlapping
    -0.06
    ation
    -0.06
    ady
    -0.06
    Debugger
    -0.06
     instead
    -0.06
    are
    -0.06
    [...,
    -0.06
     abad
    -0.06
    POSITIVE LOGITS
    nces
    0.08
    ä¸ĢèĤ¡
    0.08
    kje
    0.08
    jum
    0.08
    orc
    0.08
    cord
    0.08
     semula
    0.08
     Sej
    0.08
    æŀĿèĬ±
    0.07
    /control
    0.07
    Activations Density 0.002%

    No Known Activations