© 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. 24993
    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
    ãģ¾ãģ¾
    -0.11
    Ø©
    -0.10
    ation
    -0.09
    renz
    -0.08
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    ÑĪелÑĮ
    -0.08
    riage
    -0.08
    asmine
    -0.08
    grily
    -0.08
    hea
    -0.08
    POSITIVE LOGITS
    ly
    0.10
    äºİ
    0.10
    度çļĦ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ate
    0.08
    ments
    0.08
    度é«ĺ
    0.08
    äºİäºĭ
    0.08
    ìĸ´
    0.08
    äºİä¸ĸ
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.