© 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. 43977
    Prev
    Next
    INDEX
    Explanations

    quoted strings and structure

    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
    -0.08
     ..."
    -0.08
     ...)
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ..."
    -0.08
    **
    -0.07
    ...”
    -0.07
    ä¸İ
    -0.07
    credi
    -0.07
    \d
    -0.07
    POSITIVE LOGITS
    ingly
    0.10
    edly
    0.10
    sWith
    0.09
    iest
    0.09
    swire
    0.09
    asanya
    0.09
    åľ°è¿Ľè¡Į
    0.09
    ationToken
    0.08
    สà¹Į
    0.08
    spath
    0.08
    Activations Density 0.160%

    No Known Activations