© 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. 6993
    Prev
    Next
    INDEX
    Explanations

    reference citations

    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
    agher
    -0.14
    entication
    -0.11
    enni
    -0.10
    uum
    -0.10
    tures
    -0.10
    cpy
    -0.10
    oenix
    -0.10
    Ø·ÙĬÙĨ
    -0.10
    JECT
    -0.09
    emberg
    -0.09
    POSITIVE LOGITS
    Ùĩ
    0.20
    en
    0.17
    er
    0.17
    o
    0.16
    ä¼ĹæīĢåij¨çŁ¥
    0.16
    an
    0.16
    es
    0.16
    ä¸įåı¯æĢĿè®®
    0.14
    åĬłæĭ¿å¤§
    0.14
    æĸ°åĬłåĿ¡
    0.14
    Activations Density 0.037%

    No Known Activations