© 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. 57637
    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
    Copy
    -0.06
     copy
    -0.06
    stur
    -0.06
    ä½ľåĪĻ
    -0.06
    èµ°åĬ¿
    -0.06
    Readable
    -0.06
     breakdown
    -0.06
     anonymously
    -0.06
     break
    -0.06
    _plain
    -0.06
    POSITIVE LOGITS
    awat
    0.08
    åĽłåħ¬
    0.08
    ynchronization
    0.08
    au
    0.08
    鸳
    0.08
     Dop
    0.08
    çıĪ
    0.08
    é©
    0.08
    apu
    0.08
    ockets
    0.08
    Activations Density 0.000%

    No Known Activations