© 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. 51391
    Prev
    Next
    INDEX
    Explanations

    indentation programming phrases

    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
    _exempt
    -0.09
    ä¸ĩåį·
    -0.08
     ÑģооÑĤвеÑĤÑģÑĤвÑĥ
    -0.07
     ruled
    -0.07
    åIJijåįĹ
    -0.07
     DBNull
    -0.07
    ometro
    -0.07
    Ĥ¬
    -0.07
    éļıçĿĢæŶéĹ´çļĦ
    -0.07
     ache
    -0.07
    POSITIVE LOGITS
     hardcoded
    0.10
    æĮº
    0.08
    `
    0.07
     `
    0.07
     `_
    0.07
    è°ĥçĶ¨
    0.07
     passed
    0.07
    inser
    0.07
     presumably
    0.07
     variable
    0.07
    Activations Density 0.022%

    No Known Activations