© 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. 13413
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
    aison
    -0.09
    uard
    -0.08
    ation
    -0.08
    oyal
    -0.07
    icap
    -0.07
    bogen
    -0.07
    otion
    -0.07
    ISTRATION
    -0.07
    иÑģÑĤÑĢи
    -0.07
    ency
    -0.07
    POSITIVE LOGITS
    åĦ¿çļĦ
    0.09
    ë¦Ħ
    0.09
    mals
    0.09
    ãģªãģĮãĤī
    0.09
    ÑıÑĤ
    0.08
    URING
    0.08
    èĩªå·±èĥ½
    0.08
    Úº
    0.08
    اصÙĦ
    0.08
    uring
    0.08
    Activations Density 0.204%

    No Known Activations