© 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. 28656
    Prev
    Next
    INDEX
    Explanations

    turbochargers, fiber reinforced, sleep apnea, dental veneer, board rooms, conference rooms, index food, grade squamous

    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
    ially
    -0.08
    licated
    -0.08
    essor
    -0.08
    ulously
    -0.07
    gle
    -0.07
    gehend
    -0.07
    ucker
    -0.07
    IMUM
    -0.07
    yer
    -0.07
    ERRUPT
    -0.07
    POSITIVE LOGITS
    å±±æĻ¯åĮº
    0.08
    ãģªãģĹ
    0.07
    åįģäºĮå¹´
    0.07
    ÏĢοÏį
    0.07
    declar
    0.07
    è¿Ļ座åŁİå¸Ĥ
    0.07
    伤çĹĽ
    0.07
    è´¡
    0.07
    IID
    0.07
    å¸Ĥå§Ķå®£ä¼łéĥ¨
    0.06
    Activations Density 1.616%

    No Known Activations