© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44637
    Prev
    Next
    INDEX
    Explanations

    code and common programming words

    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
    Negative Logits
    å½»
    -0.07
    å¾¹
    -0.07
    incu
    -0.07
    esis
    -0.07
    ׾×ķ
    -0.07
    åĩij
    -0.06
    ÙIJÙĬÙħ
    -0.06
    åħĪæĿ¥
    -0.06
     tslint
    -0.06
     Raised
    -0.06
    POSITIVE LOGITS
    æIJĶ
    0.08
    PROP
    0.07
     Corpor
    0.07
    گاÙĨ
    0.07
    :],
    0.07
    å·§å¦Ļ
    0.07
    asilan
    0.07
    bbing
    0.07
    uard
    0.07
    SETTING
    0.07
    Activations Density 0.010%

    No Known Activations