© 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. 11632
    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
    软硬
    -0.08
    åĩºä¼ļ
    -0.07
    ħ
    -0.07
     mano
    -0.07
    ık
    -0.07
    软
    -0.07
    ETHER
    -0.06
     upd
    -0.06
    accio
    -0.06
    endon
    -0.06
    POSITIVE LOGITS
    DESC
    0.07
    Preview
    0.07
    -Encoding
    0.07
    oding
    0.07
    Deque
    0.07
    inet
    0.07
    uded
    0.07
    .preview
    0.07
    大ä¸įäºĨ
    0.06
    olas
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.