© 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. 63143
    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
    igre
    -0.07
    并èĮĤ
    -0.07
    ç©ºæł¼
    -0.07
    ives
    -0.07
    ungan
    -0.07
    ä½IJ
    -0.06
    åķĨæĬ¥
    -0.06
     muôn
    -0.06
    .ini
    -0.06
    ãģ®ãģ¾ãģ¾
    -0.06
    POSITIVE LOGITS
    ä¸į严
    0.08
     radius
    0.08
    flächen
    0.08
    åįĬå¾Ħ
    0.08
    Radius
    0.08
    edImage
    0.08
    lipp
    0.08
    radius
    0.08
    lymp
    0.07
     boundary
    0.07
    Activations Density 0.000%

    No Known Activations