© 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. 51366
    Prev
    Next
    INDEX
    Explanations

    negative breast, season tent, T2D, free mass

    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
    ilin
    -0.07
    acce
    -0.07
    iland
    -0.07
    icola
    -0.07
     Metr
    -0.07
    è¿ĻåĿĹ
    -0.07
    icu
    -0.07
    unde
    -0.07
    icke
    -0.06
    orna
    -0.06
    POSITIVE LOGITS
    æķĻç§ij书
    0.07
    æľ¬èº«å°±
    0.07
    lla
    0.07
    elda
    0.07
    æľ«
    0.07
     babe
    0.07
    æĹ¥æŃ¢
    0.07
    åĮºéķ¿
    0.07
    mun
    0.06
     Wiley
    0.06
    Activations Density 0.272%

    No Known Activations