© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    special characters and 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
     <!--<
    -0.09
    )["
    -0.08
     **:**
    -0.07
    VRT
    -0.07
    č↵↵
    -0.07
     **ãĢĮ
    -0.07
    `,`
    -0.07
    adi
    -0.07
    UNET
    -0.07
    é¦
    -0.07
    POSITIVE LOGITS
    â
    0.08
     [
    0.07
    ..."
    0.07
     resp
    0.07
    ‘
    0.07
     ...
    0.06
     â
    0.06
    iasi
    0.06
    ()"
    0.06
    oja
    0.06
    Activations Density 0.006%

    No Known Activations