© 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. 28491
    Prev
    Next
    INDEX
    Explanations

    retailers, links, APIs, sensors, code

    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
    untut
    -0.06
     whisk
    -0.06
    éĿŀåħ¸
    -0.06
     versatile
    -0.06
    nom
    -0.06
    ebar
    -0.06
    éĶ¦ä¸Ĭæ·»èĬ±
    -0.06
    uyo
    -0.06
    hattan
    -0.06
     sall
    -0.06
    POSITIVE LOGITS
    меÑĤо
    0.07
    amis
    0.07
    azen
    0.07
    åİĭ缩åĮħ
    0.07
    schemas
    0.07
    ÑģÑĤа
    0.07
     **:**
    0.07
    urus
    0.07
    èĭį
    0.07
    é»Ħé¾Ļ
    0.07
    Activations Density 0.003%

    No Known Activations