© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    å¾Ĺè¿ĩ
    -0.09
    ående
    -0.08
    ắt
    -0.07
    æĤī
    -0.07
     invol
    -0.07
    بد
    -0.07
    оÑĤÑĢе
    -0.07
    _tw
    -0.07
    é»Ħè±Ĩ
    -0.07
    /course
    -0.07
    POSITIVE LOGITS
    éģ¥
    0.07
    代表çĿĢ
    0.07
    çł¥
    0.07
    afd
    0.06
    代表
    0.06
     Represent
    0.06
     reaff
    0.06
    vind
    0.06
     ache
    0.06
    èĹ
    0.06
    Activations Density 0.007%

    No Known Activations