© 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. 12467
    Prev
    Next
    INDEX
    Explanations

    atomic elements and groups

    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
    Ĺı
    -0.07
     sembl
    -0.07
    oday
    -0.07
    adaptive
    -0.07
    .qq
    -0.07
     dags
    -0.07
    rov
    -0.07
     ades
    -0.07
    æĮģç»ŃåĪ°
    -0.07
    åįķä½įåĴĮ个人
    -0.07
    POSITIVE LOGITS
    rish
    0.09
    åģıæĹģ
    0.09
     atoms
    0.08
    åİŁåŃIJ
    0.08
    xygen
    0.07
     bonded
    0.07
     liberated
    0.07
     Nobel
    0.07
    è¿ŀæİ¥çļĦ
    0.07
    Connect
    0.07
    Activations Density 0.024%

    No Known Activations