© 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. 40448
    Prev
    Next
    INDEX
    Explanations

    quotation marks and programming syntax

    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
    ambat
    -0.07
    ÓĻÑĢ
    -0.07
    NESS
    -0.07
    åīª
    -0.07
    cec
    -0.06
    rvine
    -0.06
    åѦæĬ¥
    -0.06
    ievo
    -0.06
    并ä¸į代表
    -0.06
    ECH
    -0.06
    POSITIVE LOGITS
    ikin
    0.08
    dou
    0.08
    ä½łå°±æĺ¯
    0.07
     Aper
    0.07
    اط
    0.06
     Talks
    0.06
    ungkan
    0.06
    Inline
    0.06
    à¸Ħรัว
    0.06
    .lu
    0.06
    Activations Density 0.003%

    No Known Activations