© 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. 7779
    Prev
    Next
    INDEX
    Explanations

    units and measurements

    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
    æī¾åĪ°
    -0.07
    å¾Ĺæīĭ
    -0.07
    æĭ¿æĿ¥
    -0.07
     اÙĦØ£ÙĪ
    -0.07
    ecast
    -0.07
    .modules
    -0.07
    emergen
    -0.07
    .tim
    -0.07
    æī¾ä¸Ģ个
    -0.07
    èĮľ
    -0.07
    POSITIVE LOGITS
    åIJįä¹ī
    0.08
     nominal
    0.08
     represented
    0.08
    èĢĻ
    0.08
    nom
    0.07
     номина
    0.07
    .googleapis
    0.07
     behind
    0.07
     sebenarnya
    0.07
    /compiler
    0.07
    Activations Density 0.124%

    No Known Activations