© 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. 47278
    Prev
    Next
    INDEX
    Explanations

    numbers, 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
    RAR
    -0.08
    fur
    -0.07
    å¾ĭå·±
    -0.07
    ctu
    -0.07
    åĬ²
    -0.07
     Skor
    -0.06
    :first
    -0.06
    hei
    -0.06
    veis
    -0.06
    Uuid
    -0.06
    POSITIVE LOGITS
    abelle
    0.08
    丽ä¸Ŀ
    0.08
    çķ°
    0.07
    ãģĵãģ¡ãĤīãģ¯
    0.07
    çĴ°çIJĥ
    0.07
    irm
    0.07
     respectively
    0.07
    liš
    0.07
    ç¼Ń
    0.07
    rosoft
    0.06
    Activations Density 0.119%

    No Known Activations