© 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. 31467
    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
    ylon
    -0.07
    1
    -0.06
    odore
    -0.06
    minster
    -0.06
    é«ĺé£İéĻ©
    -0.06
    anol
    -0.06
    iment
    -0.06
    rowning
    -0.06
    ellen
    -0.06
    ierende
    -0.06
    POSITIVE LOGITS
    æľīäºĨå¾Ī大çļĦ
    0.08
    bouw
    0.08
    bah
    0.08
    hangi
    0.08
    åı·çļĦ
    0.08
    éĽĨåĽ¢çļĦ
    0.08
    trup
    0.08
    бÑĢÑı
    0.07
     [$
    0.07
    æ¯ıä¸Ģ份
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.