© 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. 624
    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
    Negative Logits
    _parsed
    -0.07
    _td
    -0.06
    FromArray
    -0.06
    lande
    -0.06
    _export
    -0.06
    iones
    -0.06
    landet
    -0.06
    oya
    -0.06
    ogl
    -0.05
    åı¯æıIJé«ĺ
    -0.05
    POSITIVE LOGITS
     {:.
    0.08
    cona
    0.08
    icole
    0.08
    hoven
    0.08
    miny
    0.07
    วย
    0.07
    \\\
    0.07
    éia
    0.07
    orii
    0.07
    æĬ¥éħ¬
    0.07
    Activations Density 0.000%

    No Known Activations