© 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. 12473
    Prev
    Next
    INDEX
    Explanations

    numbers and units like °C

    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
    werks
    -0.06
     mains
    -0.06
    Node
    -0.06
    alet
    -0.06
     manned
    -0.06
    kers
    -0.06
     müs
    -0.06
    ä¸Ī
    -0.06
    å¥Ĺ
    -0.06
    angled
    -0.06
    POSITIVE LOGITS
    踵
    0.07
    ucer
    0.07
    çľł
    0.07
    uÄį
    0.07
    opard
    0.07
    è´¸
    0.07
    arring
    0.07
    æĮ¯åįİ
    0.07
    osas
    0.07
    ç«¥
    0.06
    Activations Density 0.063%

    No Known Activations