© 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. 26577
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    èģ
    -0.08
    è¨Ĺ
    -0.07
    éĥ½åIJĪ
    -0.07
    untary
    -0.07
    èIJĿ
    -0.07
    eka
    -0.07
    ruž
    -0.07
    ECT
    -0.06
    -ext
    -0.06
    \\/
    -0.06
    POSITIVE LOGITS
    mars
    0.07
    ħ
    0.06
    ä¸įæĢķ
    0.06
    _STAGE
    0.06
    è¿Ļä¹Ī
    0.06
    ellan
    0.06
    à¸ŀà¸ĩ
    0.06
    maar
    0.06
    åĩºä¸Ģ份
    0.06
    chera
    0.06
    Activations Density 0.001%

    No Known Activations