© 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. 60901
    Prev
    Next
    INDEX
    Explanations

    sodium ion transport

    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
    emaine
    -0.07
    çļĦ人è¿ĺ
    -0.07
    çŃ·
    -0.07
    å¼ıçļĦ
    -0.07
    lee
    -0.07
    çijľ
    -0.07
    äºĨä»Ģä¹Ī
    -0.07
    æĸ¹åľĨ
    -0.06
    èįŁ
    -0.06
     lawy
    -0.06
    POSITIVE LOGITS
     influx
    0.08
     поÑģÑĤÑĥпа
    0.08
    åħ¥å®¤
    0.07
     Masuk
    0.07
    è¿Ľåĩº
    0.07
    åĩºåħ¥
    0.07
     entering
    0.07
    asseur
    0.07
    éĢļéģĵ
    0.07
    æµģ
    0.07
    Activations Density 0.036%

    No Known Activations