© 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. 56128
    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
    åĽłèĢĮ
    -0.07
    çļĦç¡®
    -0.07
     Frequently
    -0.07
    ä½Ĩ并ä¸į
    -0.07
    亦
    -0.06
    Util
    -0.06
    æģ°å¥½
    -0.06
    oul
    -0.06
     thereafter
    -0.06
    iven
    -0.06
    POSITIVE LOGITS
    ufa
    0.08
    ugal
    0.08
    [".
    0.08
    好çĶ¨çļĦ
    0.08
    æĬĬè¿ĻäºĽ
    0.08
    æĬĬå·¥ä½ľ
    0.08
    [email
    0.08
     tát
    0.08
    icorn
    0.08
     messed
    0.08
    Activations Density 0.000%

    No Known Activations