© 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. 23917
    Prev
    Next
    INDEX
    Explanations

    via Mediaite

    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
    nik
    -0.07
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.07
    -utils
    -0.06
    åĴĮåľ¨
    -0.06
    insky
    -0.06
    åłª
    -0.06
    .DOM
    -0.06
    -webpack
    -0.06
    çĶ¨æīĭ
    -0.06
     excessively
    -0.06
    POSITIVE LOGITS
    uton
    0.08
    ."\
    0.08
    )","
    0.08
    åIJĦ项任åĬ¡
    0.08
     cadas
    0.08
    åIJĦåľĭ
    0.07
     acom
    0.07
    endar
    0.07
     diranc
    0.07
    utre
    0.07
    Activations Density 0.033%

    No Known Activations