© 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. 21163
    Prev
    Next
    INDEX
    Explanations

    the biggest value

    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
    .gmail
    -0.07
    \xd
    -0.07
    .statusText
    -0.06
    (er
    -0.06
    oner
    -0.06
     serta
    -0.06
    -none
    -0.06
    .twitter
    -0.06
     errorCallback
    -0.06
    ClientRect
    -0.06
    POSITIVE LOGITS
    zee
    0.08
    ibur
    0.07
    ä¹ĭå®Ŀ
    0.07
    THR
    0.07
    ľ
    0.07
    enne
    0.07
    atian
    0.07
     بز
    0.06
    arro
    0.06
    ofs
    0.06
    Activations Density 0.845%

    No Known Activations