© 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. 23533
    Prev
    Next
    INDEX
    Explanations

    venous leg ulcers

    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
    lieb
    -0.07
    å·®äºĨ
    -0.06
    blatt
    -0.06
    sted
    -0.06
    ror
    -0.06
    æĭīå°Ķ
    -0.06
    æĬķåħ¥ä½¿çĶ¨
    -0.06
    åī©
    -0.06
    ÑĢал
    -0.06
    æ¡ĥæĿİ
    -0.06
    POSITIVE LOGITS
    èŁĨ
    0.08
    é©¿
    0.08
    å¥ĩéģĩ
    0.07
    EMAT
    0.07
    ãĥĵãĤ¹
    0.07
    /script
    0.07
    ousse
    0.07
    unner
    0.07
    unities
    0.07
    ãģº
    0.07
    Activations Density 0.007%

    No Known Activations