© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21717
    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
    Intersection
    -0.07
    ayani
    -0.07
    oyer
    -0.07
    imbang
    -0.07
    orsch
    -0.07
    avis
    -0.07
    quer
    -0.07
    dued
    -0.07
    .TryParse
    -0.07
    _MAT
    -0.06
    POSITIVE LOGITS
    鸳
    0.09
    ä¸ĭåIJĮ
    0.08
    ä¸Ģ段
    0.07
    ä¸Ģä½ľ
    0.07
    æįĤä½ı
    0.07
    éĴ°
    0.07
    çļĵ
    0.07
    Ada
    0.07
    åŃIJæĽ°
    0.07
    ucks
    0.06
    Activations Density 0.000%

    No Known Activations