© 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. 60120
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    kring
    -0.09
    è¿Ļ个æķħäºĭ
    -0.09
    achable
    -0.09
    ä¸ĵçĶ¨åıij票
    -0.08
    æľĿèijĹ
    -0.08
    prech
    -0.08
    å¾Īå¤ļä¸ľè¥¿
    -0.08
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.08
    umul
    -0.08
    atri
    -0.08
    POSITIVE LOGITS
    ä¸įéļ¾
    0.07
    ุ
    0.06
    _RECT
    0.06
     task
    0.06
    ç³Ł
    0.06
    anz
    0.06
    és
    0.06
    ↵
    0.06
     tasked
    0.06
    uv
    0.06
    Activations Density 0.000%

    No Known Activations