© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18852
    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
    quete
    -0.07
    æľīåĵªäºĽåij¢
    -0.07
    é²ľ
    -0.07
    婦
    -0.07
    ancel
    -0.07
    asics
    -0.07
    åĩŃä»Ģä¹Ī
    -0.07
    izi
    -0.07
    isters
    -0.07
    æĥ³èµ·æĿ¥
    -0.07
    POSITIVE LOGITS
    ç»ĵ论
    0.08
    undu
    0.08
    вок
    0.07
     tehát
    0.07
     notes
    0.07
    å¾·ç½Ĺ
    0.06
    eldes
    0.06
    isman
    0.06
    ä¸ĭæĶ¾
    0.06
     classifica
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.