© 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. 28824
    Prev
    Next
    INDEX
    Explanations

    code type annotations

    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
    che
    -0.07
    æĹłåĬŁ
    -0.07
    _DL
    -0.06
    为é¢ĺ
    -0.06
    esco
    -0.06
    prises
    -0.06
    è¿Ļ对
    -0.06
    kota
    -0.06
    eln
    -0.06
    åı·æĸĩ件
    -0.06
    POSITIVE LOGITS
    课
    0.08
    ingleton
    0.08
    stantiate
    0.07
     _)
    0.07
    _)
    0.07
    Consulta
    0.07
    iphery
    0.07
     ...)
    0.07
    )->
    0.07
    alts
    0.07
    Activations Density 0.003%

    No Known Activations