© 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. 1836
    Prev
    Next
    INDEX
    Explanations

    vascular conditions

    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
    OwnProperty
    -0.08
    ç³ľ
    -0.08
    ải
    -0.07
    oplay
    -0.07
    -chevron
    -0.07
    ikli
    -0.07
    صد
    -0.07
    ixo
    -0.07
    .lex
    -0.07
    pickle
    -0.07
    POSITIVE LOGITS
    åIJ¸è¡Ģ
    0.09
    åĩºè¡Ģ
    0.09
    æŃ¢è¡Ģ
    0.09
     veins
    0.08
    arrer
    0.08
    èľĺèĽĽ
    0.08
     spider
    0.07
    èĽĽ
    0.07
    èĻ¹
    0.07
    èıĬ
    0.07
    Activations Density 0.161%

    No Known Activations