© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63108
    Prev
    Next
    INDEX
    Explanations

    lists and phrases

    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
    Pt
    -0.07
    é¦ĸåħĪæĺ¯
    -0.07
     Nia
    -0.07
    iong
    -0.07
    rez
    -0.06
     abbreviated
    -0.06
    /interfaces
    -0.06
    æľīæĪIJ
    -0.06
    æĬ¢é²ľ
    -0.06
     compet
    -0.06
    POSITIVE LOGITS
    åĽŀè¿ĩç¥ŀ
    0.07
    idata
    0.07
    管çIJĨæľºåĪ¶
    0.07
    ãĤ«ãĤ¦ãĥ³ãĥĪ
    0.07
    人åķĬ
    0.07
    çĮ®
    0.06
    _WE
    0.06
     estip
    0.06
     brind
    0.06
    azor
    0.06
    Activations Density 0.001%

    No Known Activations