© 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. 22467
    Prev
    Next
    INDEX
    Explanations

    forward slash options

    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
    ite
    -0.07
    ynie
    -0.07
    æľ¬æĸĩæĿ¥èĩª
    -0.07
    ITE
    -0.07
    ifar
    -0.06
    [++
    -0.06
    æ±Łè·¯
    -0.06
    UNITY
    -0.06
    rypton
    -0.06
    ilere
    -0.06
    POSITIVE LOGITS
    å¼¥
    0.07
    åħĭç¦ı
    0.07
    ä»»ä½ķåħ¶ä»ĸ
    0.07
     deles
    0.07
    æ´»åĬ¨çŃī
    0.07
    allet
    0.07
    ä»ĸ们没æľī
    0.07
    "People
    0.07
    rette
    0.07
    aped
    0.07
    Activations Density 0.076%

    No Known Activations