© 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. 31545
    Prev
    Next
    INDEX
    Explanations

    save one y dataframe for each file

    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
    .charCodeAt
    -0.08
    èİ«éĿŀ
    -0.08
    Õ®
    -0.08
    .getBytes
    -0.07
     abraz
    -0.07
    .keyword
    -0.07
    éĩĩ纳çİĩ
    -0.07
    azier
    -0.07
    eof
    -0.07
    uhl
    -0.07
    POSITIVE LOGITS
    arka
    0.08
    å·¡
    0.07
    å®ļ
    0.06
    ÙĪار
    0.06
    alara
    0.06
     Exped
    0.06
    onom
    0.06
    mer
    0.06
    8
    0.06
    Ùĩب
    0.06
    Activations Density 0.188%

    No Known Activations