© 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. 26201
    Prev
    Next
    INDEX
    Explanations

    loop counters and code punctuation

    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
    äºĮèĢħ
    -0.08
    аÑģÑĤо
    -0.07
    asl
    -0.07
    ision
    -0.07
    ice
    -0.07
    ture
    -0.07
    åIJĦå¤Ħ
    -0.06
    èļĤ
    -0.06
    anto
    -0.06
    å®ĥåľ¨
    -0.06
    POSITIVE LOGITS
    วิà¸Ļ
    0.08
    fcc
    0.07
    ç»´äºļ
    0.07
    ÅŁte
    0.07
    धान
    0.07
    ÙĬÙģا
    0.07
    öp
    0.07
     Michaels
    0.07
    onal
    0.07
    sker
    0.07
    Activations Density 0.006%

    No Known Activations