© 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. 39930
    Prev
    Next
    INDEX
    Explanations

    written by screenwriter

    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
    lø
    -0.07
     Indah
    -0.07
    Į
    -0.07
    å°ıéĿĴ
    -0.07
    uras
    -0.07
     breakup
    -0.07
    urah
    -0.07
    راÙĩا
    -0.07
    ammt
    -0.07
    urm
    -0.07
    POSITIVE LOGITS
    иÑĤоÑĢ
    0.07
     post
    0.07
    ç©
    0.07
     Nus
    0.06
    buff
    0.06
    moc
    0.06
    _builder
    0.06
    .Nav
    0.06
    顶éĥ¨
    0.06
    iet
    0.06
    Activations Density 0.004%

    No Known Activations