© 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. 41237
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    ounty
    -0.06
    ì¡´
    -0.06
    ibur
    -0.06
    -0.06
    ly
    -0.06
    iaan
    -0.05
     .
    -0.05
    afi
    -0.05
    èĭįèĿĩ
    -0.05
     penn
    -0.05
    POSITIVE LOGITS
    ãĢįï¼Ī
    0.12
    ”(
    0.11
     _(
    0.11
    ãĢıï¼Ī
    0.10
    ()(
    0.10
    "](
    0.10
    >>(
    0.10
    %(
    0.10
     >(
    0.10
    è¿Ŀåıįä¸Ĭè¿°
    0.09
    Activations Density 0.274%

    No Known Activations