© 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. 47252
    Prev
    Next
    INDEX
    Explanations

    zahlen, literale, konstanten

    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
    olé
    -0.07
    angga
    -0.07
    æĽ¿
    -0.07
    ivin
    -0.06
    .handleError
    -0.06
     именно
    -0.06
    stit
    -0.06
    ANG
    -0.06
    åĩºæĿ¥
    -0.06
    r
    -0.06
    POSITIVE LOGITS
    èĢģå¸Ī说
    0.09
    大ä¸įäºĨ
    0.08
    ÑĦов
    0.08
    elim
    0.08
    oskop
    0.07
    ä»ĸ们说
    0.07
    dealloc
    0.07
    JAR
    0.07
    inz
    0.07
    -utils
    0.07
    Activations Density 0.008%

    No Known Activations