© 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. 60889
    Prev
    Next
    INDEX
    Explanations

    blood-brain barrier system

    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
    çİīçݯ
    -0.08
    èĤºæ°Ķ
    -0.08
    裤
    -0.08
    eix
    -0.08
    chants
    -0.07
    lung
    -0.07
    è£Ĩ
    -0.07
    שר
    -0.07
    çĦ
    -0.07
    é£İ管
    -0.07
    POSITIVE LOGITS
    èĦij
    0.18
     brain
    0.18
     Brain
    0.16
    大èĦij
    0.15
    Brain
    0.15
     neurological
    0.15
    ç¥ŀç»ı
    0.15
    brain
    0.15
     neuro
    0.15
     cerebral
    0.15
    Activations Density 0.583%

    No Known Activations