© 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. 20261
    Prev
    Next
    INDEX
    Explanations

    pain, inflammation, injury

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    éĢ
    -0.08
    缺éĻ·
    -0.07
    ä¿Ĭ
    -0.07
    ehlen
    -0.07
     fatally
    -0.07
     carved
    -0.07
    åѤåĦ¿
    -0.06
    çī¢çī¢æĬĬæı¡
    -0.06
     dwar
    -0.06
    ncio
    -0.06
    POSITIVE LOGITS
    åıijçĤİ
    0.10
     irritation
    0.10
     swollen
    0.10
    红èĤ¿
    0.09
    çĸ¼çĹĽ
    0.09
    轻微çļĦ
    0.08
    èĤ¿çĹĽ
    0.08
    çĤİçĹĩ
    0.08
     inflammation
    0.08
    åĪ©çī©
    0.08
    Activations Density 0.087%

    No Known Activations