© 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. 29485
    Prev
    Next
    INDEX
    Explanations

    ischemia

    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
    çļĦ身
    -0.08
    .mk
    -0.07
    ±
    -0.07
     carri
    -0.07
    åĢ¾
    -0.07
    vinc
    -0.07
    ุà¹Īà¸ĩ
    -0.07
     Jenner
    -0.07
    宿
    -0.07
    èĢģåİ»
    -0.07
    POSITIVE LOGITS
    缺氧
    0.12
    æĨĭ
    0.08
    缺è¡Ģ
    0.08
    æ°§
    0.08
    çĶŁåŃĺ
    0.08
    çĶŁåŃĺçļĦ
    0.08
     zones
    0.08
    éħ¸ç´ł
    0.08
     oxygen
    0.08
     survival
    0.07
    Activations Density 0.105%

    No Known Activations