© 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. 50750
    Prev
    Next
    INDEX
    Explanations

    print statements in code

    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
    اردة
    -0.09
    asher
    -0.08
    æ²¹çĽIJ
    -0.08
    stry
    -0.07
    inage
    -0.07
    cki
    -0.07
    ä¹IJä¹İ
    -0.07
    czyk
    -0.07
     dưỡng
    -0.07
     ë§IJìĿ´
    -0.07
    POSITIVE LOGITS
    èIJį
    0.07
    ä¸ĢæŶçļĦ
    0.07
    ned
    0.06
    wand
    0.06
    ÑĢемен
    0.06
    str
    0.06
    metic
    0.06
     заÑĢ
    0.06
    lint
    0.06
    Hi
    0.06
    Activations Density 0.009%

    No Known Activations