© 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. 24531
    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
    æ´»
    -0.08
    åľ¨äºº
    -0.07
    åĩºçİ°åľ¨äºĨ
    -0.07
    åĪ°äºº
    -0.06
    åĬłæĸ¯
    -0.06
    engk
    -0.06
    ¯
    -0.06
    临æŶ
    -0.06
    ependency
    -0.06
    åįİ缼
    -0.06
    POSITIVE LOGITS
    eron
    0.10
    管çIJĨç±»
    0.08
    好åķ¦
    0.08
    TVT
    0.08
    ubr
    0.07
    erset
    0.07
    _ttl
    0.07
    åĵªæľī
    0.07
    ä¼¼æĺ¯
    0.07
     divul
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.