© 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. 44240
    Prev
    Next
    INDEX
    Explanations

    punctuation or closing delimiters

    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
    鼷æĸ¯
    -0.07
    åĪĻ以
    -0.07
    èches
    -0.07
    以åıĬ对
    -0.07
    ?):
    -0.06
    åĪĻ表示
    -0.06
    åĪĻåı¯ä»¥
    -0.06
     themselves
    -0.06
    bam
    -0.06
    åĪĻæľī
    -0.06
    POSITIVE LOGITS
    aq
    0.07
    åĭī
    0.07
    ometrics
    0.07
    ucks
    0.07
    claimer
    0.07
    èĻ½å°ı
    0.07
    دÙĬØ©
    0.07
    ä¸ĸ
    0.07
    omet
    0.07
    arent
    0.07
    Activations Density 0.005%

    No Known Activations