© 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. 4513
    Prev
    Next
    INDEX
    Explanations

    markdown file

    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
    严
    -0.08
    欢è¿İ访éĹ®
    -0.07
    åŁºäºİ
    -0.07
    ä¸įæķ£
    -0.07
     Masjid
    -0.07
    elig
    -0.06
    maat
    -0.06
    TypeEnum
    -0.06
    åIJįèĥľ
    -0.06
    éĿ¢è²Į
    -0.06
    POSITIVE LOGITS
    incar
    0.07
    @qq
    0.07
    é¼İ
    0.06
    celet
    0.06
    _SCOPE
    0.06
    .charAt
    0.06
    coop
    0.06
     aff
    0.06
    APO
    0.06
    cope
    0.06
    Activations Density 0.001%

    No Known Activations