© 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. 33988
    Prev
    Next
    INDEX
    Explanations

    visiting websites or nodes

    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
    zinho
    -0.09
    eon
    -0.08
    kenntnisse
    -0.08
    ggia
    -0.08
    alic
    -0.08
    ilda
    -0.08
    ../../../../
    -0.08
    atically
    -0.08
    veau
    -0.07
    headed
    -0.07
    POSITIVE LOGITS
    OrCreate
    0.11
    aries
    0.07
    osity
    0.07
    urig
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
     versa
    0.07
    cosity
    0.07
    ê°Ŀ
    0.07
    é¦ģ
    0.07
    ÙĤات
    0.07
    Activations Density 0.032%

    No Known Activations