© 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. 49060
    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
    abili
    -0.07
    elihood
    -0.07
     reca
    -0.07
    inten
    -0.07
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.07
    ableObject
    -0.07
    梢
    -0.07
    Initialized
    -0.07
    ÑĢÑıд
    -0.07
    fields
    -0.07
    POSITIVE LOGITS
    áli
    0.07
    åİ®
    0.06
     Tuấn
    0.06
    uez
    0.06
    ÑĢÑĥÑĤ
    0.06
     #:
    0.06
    Ñħол
    0.06
    åĨħ容åĴĮ
    0.06
    å¿ĥ裡
    0.06
    å¿ĥç¥ŀ
    0.06
    Activations Density 0.000%

    No Known Activations