© 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. 61202
    Prev
    Next
    INDEX
    Explanations

    pulmonary vascular and artery

    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
     autoc
    -0.08
    ä¸Ń庸
    -0.08
     alphanumeric
    -0.07
    anken
    -0.07
    åĿĤ
    -0.07
    PARSE
    -0.07
    _MA
    -0.07
    彬
    -0.07
     logarith
    -0.07
    orian
    -0.07
    POSITIVE LOGITS
     pressures
    0.08
    åĬłåİĭ
    0.08
     pressure
    0.08
    å£ĵ
    0.07
    -pressure
    0.07
    åİĭ
    0.07
     Gart
    0.07
    pressure
    0.07
    ìĪľ
    0.07
    twitter
    0.07
    Activations Density 0.055%

    No Known Activations