© 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. 49766
    Prev
    Next
    INDEX
    Explanations

    linking code attributes

    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
    æī¬
    -0.07
    ¨
    -0.07
    鸥
    -0.07
    ä¸įä¼ļæĺ¯
    -0.07
    ô
    -0.07
    ob
    -0.06
    um
    -0.06
    士æŀĹ
    -0.06
    ogen
    -0.06
    æľ¬é¢ĺ
    -0.06
    POSITIVE LOGITS
    ÙĥÙĬÙĦ
    0.09
    ucci
    0.07
    SENT
    0.07
    azos
    0.07
    ngle
    0.07
    :model
    0.07
    placer
    0.07
    ÙĥÙī
    0.07
    gene
    0.07
    lij
    0.07
    Activations Density 0.393%

    No Known Activations