© 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. 40125
    Prev
    Next
    INDEX
    Explanations

    rheumatoid arthritis

    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
     eject
    -0.08
    èĢĺ
    -0.08
    erland
    -0.08
    两级
    -0.07
    éĹ»
    -0.07
    FragmentManager
    -0.07
    åĮĸç²ªæ±ł
    -0.07
     traumatis
    -0.07
    toon
    -0.07
    ç²ªæ±ł
    -0.07
    POSITIVE LOGITS
    ç±»é£İ湿
    0.10
    é£İ湿
    0.09
     arthritis
    0.09
    æĢ§åħ³èĬĤçĤİ
    0.08
    çĹ¹
    0.08
    游走
    0.08
     rhe
    0.08
     ÑģÑĥÑģÑĤав
    0.07
     pain
    0.07
    åħ³èĬĤçĤİ
    0.07
    Activations Density 0.108%

    No Known Activations