© 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. 29114
    Prev
    Next
    INDEX
    Explanations

    release

    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
    çŁĹ
    -0.06
    æĺı
    -0.06
    ØŃÙĬØ©
    -0.06
     elev
    -0.06
    å¾Ĺèµ·
    -0.06
     mush
    -0.06
    æ¯Ĵ
    -0.06
    nu
    -0.06
    à¹Ħวà¹ī
    -0.06
    fus
    -0.06
    POSITIVE LOGITS
    éĩĬæĶ¾åĩº
    0.12
    éĩĬæĶ¾
    0.11
     releasing
    0.10
     releases
    0.09
    éĩĭæĶ¾
    0.09
    -release
    0.09
    /release
    0.09
     release
    0.09
     Release
    0.09
    _release
    0.09
    Activations Density 0.030%

    No Known Activations