© 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. 12541
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and programming symbols

    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
    _bal
    -0.08
    mlink
    -0.08
    ienz
    -0.08
    ÑĢеÑı
    -0.08
    ignon
    -0.08
    士
    -0.08
    éĿĵ
    -0.08
    ait
    -0.08
    .setScale
    -0.08
    åIJĪçIJĨ
    -0.08
    POSITIVE LOGITS
     shadow
    0.07
    actual
    0.07
     actual
    0.07
     fro
    0.06
     Perc
    0.06
    sharp
    0.06
    åįĹå±±
    0.06
     its
    0.06
    Actual
    0.06
    shadow
    0.06
    Activations Density 0.077%

    No Known Activations