© 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. 51945
    Prev
    Next
    INDEX
    Explanations

    output is : or output of

    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
    被æµıè§Ī
    -0.08
    åİ»è¿ĩ
    -0.08
    æľīä½į
    -0.08
    å°±å¾Ģ
    -0.07
    ç½ijç«Ļ导èĪª
    -0.07
    zysta
    -0.07
    anta
    -0.07
    æĿ¥äºº
    -0.07
    纵横
    -0.07
    ibrary
    -0.07
    POSITIVE LOGITS
    è¾ĵåĩº
    0.09
     Output
    0.08
    æīĵåį°
    0.08
    output
    0.08
    Output
    0.08
    æ·ĺ
    0.08
     output
    0.07
     prints
    0.07
    /output
    0.07
     Ausgabe
    0.07
    Activations Density 0.011%

    No Known Activations