© 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. 64451
    Prev
    Next
    INDEX
    Explanations

    hypoxic vasoconstriction

    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
    袤
    -0.07
    ØŃÙĦØ©
    -0.07
    ä¿¡çļĦ
    -0.07
    геÑĢ
    -0.07
    entai
    -0.07
    èĭ±éĽĦçļĦ
    -0.07
     Bair
    -0.07
     GetComponent
    -0.07
    ä¹Łæĺ¯è¿Ļæł·
    -0.07
     Lot
    -0.07
    POSITIVE LOGITS
    èĤł
    0.07
    åĬłåĪĨ
    0.07
    encies
    0.06
    湿
    0.06
    è¯ļ
    0.06
    paused
    0.06
    eth
    0.06
    "bytes
    0.06
     Wiley
    0.06
    å±ħ
    0.06
    Activations Density 0.045%

    No Known Activations