© 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. 63966
    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
    orton
    -0.07
    igin
    -0.07
    AuthProvider
    -0.07
    ofile
    -0.07
    /activity
    -0.07
    ulti
    -0.07
    lest
    -0.07
    åĮĸéªĮ
    -0.07
    èĨ¨
    -0.07
    EventListener
    -0.06
    POSITIVE LOGITS
    ench
    0.08
    imeo
    0.07
    -U
    0.06
    iard
    0.06
    -utils
    0.06
     vim
    0.06
    ÑģÑĤеÑĢ
    0.06
    èĢĺ
    0.06
    -Ta
    0.06
    новÑĢемен
    0.06
    Activations Density 0.000%

    No Known Activations