© 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. 29244
    Prev
    Next
    INDEX
    Explanations

    `.com domain or code elements

    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
    ض
    -0.07
    resher
    -0.07
    åįĹçľģ
    -0.07
    åIJīæĸ¯
    -0.07
    åħ³ä¹İ
    -0.07
    大ä¹ī
    -0.07
    åľ¨èIJ¥
    -0.06
    à´¿à´²àµįà´²
    -0.06
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.06
    åİĭä¸ĭ
    -0.06
    POSITIVE LOGITS
    igraf
    0.07
    زÙĬÙĦ
    0.07
    åħ·æľīè¾ĥé«ĺçļĦ
    0.07
    oux
    0.06
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.06
    ÙĪاد
    0.06
    è¿ĺä¸įåĪ°
    0.06
    WithPath
    0.06
    ä¸ļåįıä¼ļ
    0.06
    ÙĤاطع
    0.06
    Activations Density 0.007%

    No Known Activations