© 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. 21986
    Prev
    Next
    INDEX
    Explanations

    following lists

    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
    ukum
    -0.07
    åĽĽåij¨
    -0.07
    arena
    -0.06
    รà¹īà¸Ńà¸Ļ
    -0.06
    enge
    -0.06
    erii
    -0.06
    rano
    -0.06
    .Focus
    -0.06
     conclus
    -0.06
    .Concurrent
    -0.06
    POSITIVE LOGITS
    ittings
    0.08
    æĵį
    0.07
    plements
    0.07
     kinds
    0.07
    ÙİÙijا
    0.07
    emons
    0.07
    adders
    0.07
    éķ¿ä¹ħ
    0.07
    ths
    0.06
    åĪĺ家
    0.06
    Activations Density 0.004%

    No Known Activations