© 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. 60961
    Prev
    Next
    INDEX
    Explanations

    printf or stdout

    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
    urr
    -0.07
    è¦ģä¿Ŀè¯ģ
    -0.07
    zel
    -0.07
    еÑĤен
    -0.07
    为äºĨä¿Ŀè¯ģ
    -0.07
    å¼¥åĭĴ
    -0.06
    å½Ĵ
    -0.06
    eras
    -0.06
    设为
    -0.06
    ault
    -0.06
    POSITIVE LOGITS
    .stdout
    0.08
    _display
    0.08
    è¾ĵåĩº
    0.08
     prints
    0.08
    .print
    0.08
     displaying
    0.08
    isplay
    0.08
    STDOUT
    0.08
     Prints
    0.08
     STDOUT
    0.08
    Activations Density 0.376%

    No Known Activations