© 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. 63180
    Prev
    Next
    INDEX
    Explanations

    browser vendor prefixes for css

    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
    utel
    -0.08
    okit
    -0.07
    çĵ¤
    -0.07
    è¿Ķè¿ĺ
    -0.07
    ην
    -0.07
    éĩ
    -0.07
    schnitt
    -0.07
    ublisher
    -0.07
    è¿ĶåĽŀåĢ¼
    -0.07
    -INF
    -0.07
    POSITIVE LOGITS
    itta
    0.07
    å¾Ĵ
    0.07
    atha
    0.07
    èĪ
    0.07
    ADE
    0.06
    ade
    0.06
    ä¸Ĭä¸Ģ
    0.06
    gc
    0.06
    ath
    0.06
    Thread
    0.06
    Activations Density 0.001%

    No Known Activations