© 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. 26469
    Prev
    Next
    INDEX
    Explanations

    complex medical conditions

    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
    åįģæĿ¡
    -0.08
    åħ´éļĨ
    -0.07
     Ministère
    -0.07
    iap
    -0.07
    ës
    -0.07
    ilé
    -0.06
    untut
    -0.06
    çijļ
    -0.06
     Spuren
    -0.06
    åIJĮæĹ¶å¯¹
    -0.06
    POSITIVE LOGITS
    çī¹å®ļãģ®
    0.09
    çī¹å®ļ
    0.08
    象
    0.07
    arth
    0.07
    ood
    0.07
     supposedly
    0.07
     pros
    0.07
    ä¸ĵæľī
    0.07
    èĬ¬
    0.07
    araan
    0.07
    Activations Density 0.673%

    No Known Activations