© 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. 47741
    Prev
    Next
    INDEX
    Explanations

    code comment headers

    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
    essian
    -0.07
    AppDelegate
    -0.06
    imson
    -0.06
    稿
    -0.06
    assi
    -0.06
    incy
    -0.06
    uncture
    -0.06
    ailable
    -0.06
    _processes
    -0.06
    ilateral
    -0.06
    POSITIVE LOGITS
     Rodrig
    0.07
    æķ°åĴĮ
    0.07
    _regex
    0.07
    utri
    0.06
    нÑı
    0.06
     cerem
    0.06
    ÑĤана
    0.06
    ubb
    0.06
    åĸ¬
    0.06
    acce
    0.06
    Activations Density 2.322%

    No Known Activations