© 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. 13764
    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
    chy
    -0.07
    ellini
    -0.07
    æĿ¥åºĹ
    -0.07
    imps
    -0.07
    mob
    -0.07
    æĢĴæĶ¾
    -0.07
    aces
    -0.07
    ieri
    -0.07
    osso
    -0.07
     //{
    -0.07
    POSITIVE LOGITS
     princip
    0.08
    onav
    0.07
     INFORMA
    0.07
    ç¥ĸåĽ½çļĦ
    0.07
    asics
    0.07
    vär
    0.07
    èı²çī¹
    0.07
    ä¸Ģè¿ŀ
    0.07
    _ADAPTER
    0.07
    à¹Ĭ
    0.07
    Activations Density 0.000%

    No Known Activations