© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 721
    Prev
    Next
    INDEX
    Explanations

    code keys and values

    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
    Negative Logits
     Carton
    -0.07
    åĴĮ群ä¼Ĺ
    -0.07
    åIJ¯
    -0.07
    eu
    -0.06
    iru
    -0.06
    owers
    -0.06
    åIJ¯åıij
    -0.06
    椿
    -0.06
    iena
    -0.06
    åĨįæľī
    -0.06
    POSITIVE LOGITS
    çĽĬçĶŁ
    0.08
    èĬĻ
    0.08
    INGTON
    0.07
    èijĽ
    0.07
    ä»ĸ乡
    0.07
    请çĻ»å½ķ
    0.07
    Ñĩиной
    0.07
    wahl
    0.07
    -custom
    0.07
    æķħ
    0.07
    Activations Density 0.235%

    No Known Activations