© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23417
    Prev
    Next
    INDEX
    Explanations

    mathematical terms functions constants matrix

    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
    ulang
    -0.08
    quil
    -0.08
    ãĥ¼ãĤ¸ãĥ£
    -0.08
     collet
    -0.07
    Ñģен
    -0.07
    rotch
    -0.07
    apy
    -0.07
     Teg
    -0.07
    ÙĪدÛĮ
    -0.07
    ä¹ĭæĢ¥
    -0.07
    POSITIVE LOGITS
    iskan
    0.07
    åIJį为
    0.06
    ant
    0.06
    å¸Īå¾·
    0.06
    PM
    0.06
    -inspired
    0.06
     G
    0.06
     h
    0.06
     bernama
    0.06
     '
    0.06
    Activations Density 0.059%

    No Known Activations