© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17572
    Prev
    Next
    INDEX
    Explanations

    dialysis patients

    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
     slog
    -0.08
    WithOptions
    -0.08
    èİ«åıĬ
    -0.08
    è¡ĮåĬ¨æĸ¹æ¡Ī
    -0.07
    umb
    -0.07
    adge
    -0.07
     WithEvents
    -0.07
    以西
    -0.07
    åĨįæİ¥
    -0.07
    -options
    -0.07
    POSITIVE LOGITS
    èģļ
    0.06
    ucie
    0.06
     related
    0.06
    ajaan
    0.06
     Dress
    0.06
    acula
    0.06
    讨好
    0.06
    _related
    0.06
    缸åħ³åĨħ容
    0.06
    å¾ĹäºĨ
    0.06
    Activations Density 0.906%

    No Known Activations