© 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. 57943
    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
    éĽĨä¸Ń
    -0.08
    ylvania
    -0.08
    afc
    -0.08
    yiz
    -0.07
    ãģ¾ãĤĵ
    -0.07
    åı¦
    -0.07
    zos
    -0.07
    梦å¯IJ以æ±Ĥ
    -0.07
    ardini
    -0.07
    avons
    -0.07
    POSITIVE LOGITS
    ¼
    0.07
    schau
    0.07
    heit
    0.07
    ä¸İ建议
    0.07
    sis
    0.07
    nett
    0.07
    åĪ©æĸ¯
    0.07
    iria
    0.06
    iÄį
    0.06
    ouble
    0.06
    Activations Density 0.000%

    No Known Activations