© 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. 26410
    Prev
    Next
    INDEX
    Explanations

    compact design or footprint

    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
    orej
    -0.07
    hare
    -0.07
    è®¤çľŁçłĶ究
    -0.07
    /OR
    -0.07
    OME
    -0.07
    dorf
    -0.07
    доми
    -0.07
    оÑĢе
    -0.07
    omme
    -0.07
    æķħäºĭæĥħ
    -0.07
    POSITIVE LOGITS
    éĢĢåĮĸ
    0.07
    ä¸Ń西åĮ»
    0.07
    иÑģÑĤи
    0.07
    å½±
    0.07
    اذ
    0.07
    对åºĶ
    0.07
    går
    0.07
    _expect
    0.06
    egd
    0.06
     retreat
    0.06
    Activations Density 0.058%

    No Known Activations