© 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. 8548
    Prev
    Next
    INDEX
    Explanations

    numeric or boolean flags, options

    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
     Brus
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.06
    inker
    -0.06
    illy
    -0.06
    没
    -0.06
    èĢĮ论
    -0.06
    cola
    -0.06
    adak
    -0.06
    alak
    -0.06
    ÑģнÑĥ
    -0.06
    POSITIVE LOGITS
    uccio
    0.08
    åijĽ
    0.07
    -desc
    0.07
    سÙĪÙĨ
    0.07
    laf
    0.07
    onas
    0.07
    大æīĭ
    0.07
    ,options
    0.07
    æĢĿ
    0.07
    egro
    0.06
    Activations Density 0.293%

    No Known Activations