© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    football-only member, split squad, late trading

    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
    åĵī
    -0.07
    ×ķ×ŀר
    -0.07
    ²
    -0.07
    个人æĪĸ
    -0.07
    çĹħç¨ĭ
    -0.07
    æĺķ
    -0.07
    pers
    -0.06
    بÙĨ
    -0.06
     Fund
    -0.06
     ipsum
    -0.06
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.09
    eluk
    0.08
    htable
    0.08
    nown
    0.08
    jim
    0.08
    TTg
    0.08
    nop
    0.07
    -slide
    0.07
    fee
    0.07
    ãģªãģĮãĤī
    0.07
    Activations Density 0.406%

    No Known Activations