© 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. 22088
    Prev
    Next
    INDEX
    Explanations

    non-decreasing, at least as large

    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
    celer
    -0.07
    è¿ijåľ¨
    -0.07
    åıijçİ°åľ¨
    -0.07
    ä¸įåģľçļĦ
    -0.07
    edef
    -0.07
    ducted
    -0.07
     ni
    -0.06
    achen
    -0.06
    alap
    -0.06
    urio
    -0.06
    POSITIVE LOGITS
    endor
    0.08
    ä¸įè¿ĺ
    0.08
    endorf
    0.08
    ä¸įå°ıäºİ
    0.07
    esm
    0.07
    bles
    0.07
    pect
    0.07
    sem
    0.07
    éĻIJ度
    0.07
     toller
    0.07
    Activations Density 0.014%

    No Known Activations