© 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. 40015
    Prev
    Next
    INDEX
    Explanations

    icon or svg elements

    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
    <|box_end|>
    -0.08
    kees
    -0.07
    asser
    -0.07
    oth
    -0.07
    iers
    -0.07
    èĮ¨
    -0.07
    reno
    -0.07
    èŁĴ
    -0.06
    .addAll
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
     icon
    0.09
    Svg
    0.08
     emblem
    0.08
     ìķĦìĿ´ì½ĺ
    0.08
    Icon
    0.08
     iconic
    0.07
    /icons
    0.07
    -mini
    0.07
    _icon
    0.07
    åīª
    0.07
    Activations Density 0.110%

    No Known Activations