© 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. 19224
    Prev
    Next
    INDEX
    Explanations

    starts a question

    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
    wad
    -0.07
    IAL
    -0.07
    æºIJè¿ľæµģ
    -0.07
    ä¼ļè®®æĮĩåĩº
    -0.07
    cesa
    -0.07
    ob
    -0.07
    ILING
    -0.06
    ä¸įäºī
    -0.06
    åĬ¿åľ¨å¿ħ
    -0.06
    à¸Ķุ
    -0.06
    POSITIVE LOGITS
    ?[
    0.08
    rite
    0.07
     же
    0.07
     ÑģобÑģÑĤвенно
    0.07
     retrospect
    0.07
    ?)
    0.07
    (Query
    0.07
    ?(
    0.06
    ewise
    0.06
    ?):
    0.06
    Activations Density 0.070%

    No Known Activations