© 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. 9650
    Prev
    Next
    INDEX
    Explanations

    bash, python, and perl scripts

    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
    [sizeof
    -0.10
     Millenn
    -0.10
    å¾·éŁ³
    -0.10
    åĴĮ讯
    -0.10
    æľ¬ç½ijç«Ļ
    -0.09
    loff
    -0.09
    @js
    -0.09
    datal
    -0.09
    zbollah
    -0.09
    munition
    -0.09
    POSITIVE LOGITS
    ↵
    0.08
    !
    0.07
    ↵↵
    0.07
    2
    0.07
    3
    0.06
    “
    0.06
    ”
    0.06
    ;
    0.06
    ulla
    0.06
    åľ¨è¿Ļä¸Ģ
    0.05
    Activations Density 0.354%

    No Known Activations