© 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. 55447
    Prev
    Next
    INDEX
    Explanations

    describing/description

    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
    /her
    -0.09
    itchens
    -0.09
    .parseFloat
    -0.09
    irth
    -0.09
    ศà¸Ī
    -0.09
    ÑĤен
    -0.09
    ropa
    -0.09
    ÙĪÙĬØ©
    -0.09
    ãģ¤æĺŁ
    -0.08
    olland
    -0.08
    POSITIVE LOGITS
    o
    0.08
    veloper
    0.08
     ulang
    0.08
    æ¸ħæ¥ļ
    0.07
    criptive
    0.07
    cript
    0.07
    cribing
    0.06
    оÑĢо
    0.06
     lÆ°á»Ŀng
    0.06
    Ñİ
    0.06
    Activations Density 0.124%

    No Known Activations