© 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. 40244
    Prev
    Next
    INDEX
    Explanations

    string formatting (printf, sprintf, format)

    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
    oo
    -0.07
    ä¹ı
    -0.06
    æľīåģ¿
    -0.06
    ood
    -0.06
    ptom
    -0.06
     substance
    -0.06
    _argument
    -0.06
    å¿ħ须注æĺİ
    -0.06
    oom
    -0.06
    èIJ¥ä¸ļæī§çħ§
    -0.06
    POSITIVE LOGITS
    anea
    0.09
    éĺħè¯»æľ¬æĸĩ
    0.09
    inaan
    0.08
     Macros
    0.08
    itev
    0.08
     eksk
    0.08
    ongen
    0.08
    ateur
    0.08
    illeurs
    0.08
    è¡Įèĩ³
    0.07
    Activations Density 0.048%

    No Known Activations