© 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. 55281
    Prev
    Next
    INDEX
    Explanations

    punctuations and code separators

    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
    essel
    -0.07
     himself
    -0.07
    aton
    -0.07
    ä¸Ģè·¯
    -0.07
    еÑģÑĮ
    -0.07
    ylon
    -0.07
    plan
    -0.06
    geist
    -0.06
    izon
    -0.06
    iem
    -0.06
    POSITIVE LOGITS
    æĸ°èĪĪ
    0.08
    #'
    0.07
    notated
    0.07
    жÑij
    0.07
    iders
    0.07
    obet
    0.07
    ynchronized
    0.07
    åĩĨç¡®åľ°
    0.07
    endcode
    0.07
    渴
    0.07
    Activations Density 0.009%

    No Known Activations