© 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. 46590
    Prev
    Next
    INDEX
    Explanations

    Advent, Vivid, Romany, onset, stepwise, Countdown, Advertiser

    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
    \\/
    -0.07
    -fw
    -0.06
    itimate
    -0.06
    {\"
    -0.06
    ÑģÑĤанавли
    -0.06
    è¿Ļè¾¹çļĦ
    -0.06
    åı«ä»ĸ
    -0.06
    oth
    -0.06
    ä¸ĩæĸ¹
    -0.06
    (LP
    -0.06
    POSITIVE LOGITS
    _RENDER
    0.07
    idar
    0.07
    ifen
    0.07
    _tokenize
    0.06
    ghan
    0.06
    iven
    0.06
    ä¸įå°½
    0.06
    stry
    0.06
     Finan
    0.06
    неÑĢа
    0.06
    Activations Density 0.387%

    No Known Activations