© 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. 64652
    Prev
    Next
    INDEX
    Explanations

    endothelial cells

    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
    голо
    -0.08
    aksin
    -0.08
    -ending
    -0.08
    [target
    -0.08
    eful
    -0.08
    ocache
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    ongyang
    -0.07
    saus
    -0.07
    nier
    -0.07
    POSITIVE LOGITS
    -mediated
    0.09
     mediator
    0.09
    -derived
    0.07
     mediated
    0.07
     Neville
    0.07
    æĿ¥èĩªäºİ
    0.06
    æĿ¥æºIJäºİ
    0.06
     mediation
    0.06
    æĿ¥èĩª
    0.06
    medi
    0.06
    Activations Density 0.176%

    No Known Activations