© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16093
    Prev
    Next
    INDEX
    Explanations

    pairs of

    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
    reens
    -0.07
    è¡Ķ
    -0.07
    incer
    -0.06
    æŀĿ
    -0.06
    nav
    -0.06
    éĤ£é¢Ĺ
    -0.06
    ä½IJ
    -0.06
    ä¸Ģè¨Ģ
    -0.06
    insen
    -0.06
    ibes
    -0.06
    POSITIVE LOGITS
     pairs
    0.17
    pairs
    0.15
    æ¯ıç»Ħ
    0.14
    _pairs
    0.13
    Pairs
    0.13
    éħį对
    0.12
     pairing
    0.12
    (pair
    0.11
     pair
    0.11
    .pair
    0.11
    Activations Density 0.015%

    No Known Activations