© 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. 4561
    Prev
    Next
    INDEX
    Explanations

    extracting content, text, or strings

    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
    gow
    -0.09
    immel
    -0.07
    ¯
    -0.07
    unday
    -0.07
    inkle
    -0.07
    cratch
    -0.07
     probes
    -0.07
    æĻı
    -0.07
    fusion
    -0.07
    ÕŃ
    -0.07
    POSITIVE LOGITS
    æıIJåıĸ
    0.11
    Extractor
    0.10
     extracting
    0.09
    .extract
    0.09
    Extract
    0.09
    åĩ¡
    0.09
     extract
    0.09
    extract
    0.09
    åıªè¦ģæĺ¯
    0.09
    _extract
    0.09
    Activations Density 0.085%

    No Known Activations