© 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. 17384
    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
    aline
    -0.07
    inati
    -0.06
    asco
    -0.06
    avi
    -0.06
     indeed
    -0.06
    omas
    -0.06
     dumb
    -0.06
    enum
    -0.06
     g
    -0.06
    Extensions
    -0.06
    POSITIVE LOGITS
    asten
    0.09
    éīĽ
    0.09
    éĵħ
    0.08
     olev
    0.07
    _Variable
    0.07
    htable
    0.07
     #__
    0.07
    /key
    0.07
    ollar
    0.07
    --,
    0.07
    Activations Density 0.000%

    No Known Activations