© 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. 40199
    Prev
    Next
    INDEX
    Explanations

    scientific analysis and measurement

    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
    å±¥
    -0.09
    kau
    -0.08
    ifes
    -0.08
    eng
    -0.07
    enges
    -0.07
     padd
    -0.07
    ç«Ļéķ¿
    -0.07
    epad
    -0.07
     padded
    -0.07
    fü
    -0.07
    POSITIVE LOGITS
    æľīèĩ´
    0.07
     concentrations
    0.07
    esis
    0.07
     precip
    0.07
     pH
    0.07
     metast
    0.07
    并åIJĮæŶ
    0.07
    æĶ¾è¿ĩ
    0.06
    pheres
    0.06
    ysis
    0.06
    Activations Density 0.003%

    No Known Activations