© 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. 63305
    Prev
    Next
    INDEX
    Explanations

    airway obstruction and breathing difficulties

    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
    umat
    -0.09
    èħ°éħ¸
    -0.08
    裾
    -0.08
    伤çĹĽ
    -0.07
    tras
    -0.07
    踵
    -0.07
    åıĺåĬ¨
    -0.07
    è®Ĭåĭķ
    -0.07
    çĺ¸
    -0.07
     streak
    -0.07
    POSITIVE LOGITS
    çªĴæģ¯
    0.12
    æ°Ķéģĵ
    0.10
     airflow
    0.10
     choking
    0.10
    åĸī
    0.10
     ventil
    0.09
     respiratory
    0.09
    æ°Ķ管
    0.09
     breathing
    0.09
     obstruct
    0.09
    Activations Density 0.077%

    No Known Activations