© 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. 57997
    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
    åģľä¸ļ
    -0.08
    è¯¥åĽ½
    -0.08
    Âł
    -0.07
    ä¸ĢçĤ¹åĦ¿
    -0.06
    åįģæĿ¡
    -0.06
    åľ°å¤´
    -0.06
    éħįç½®æĸ¹éĿ¢
    -0.06
    èī¯
    -0.06
     [...]
    -0.06
     Mut
    -0.06
    POSITIVE LOGITS
    orsa
    0.08
    аве
    0.08
    ä¸Ģ覧
    0.08
    BuilderFactory
    0.08
     Ames
    0.08
    esub
    0.07
    ovie
    0.07
    -keys
    0.07
    gmail
    0.07
    å®Ŀåħ¸
    0.07
    Activations Density 0.000%

    No Known Activations