© 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. 37975
    Prev
    Next
    INDEX
    Explanations

    sampling, surveying, capturing fauna

    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
     Manufacturing
    -0.08
     genu
    -0.07
    足åĿĽ
    -0.07
    Manufact
    -0.07
    å¤ĩæ¡Īåı·
    -0.07
     manufacturing
    -0.07
    åĪ¶éĢłå·¥èīº
    -0.07
    æµ·ãģ®
    -0.07
    FAULT
    -0.07
    /dev
    -0.07
    POSITIVE LOGITS
     sightings
    0.10
     sampling
    0.08
     census
    0.08
    é¢ij次
    0.08
     fauna
    0.08
    ARAM
    0.08
    æĢ»æķ°çļĦ
    0.08
    GPS
    0.08
     roadside
    0.08
     informant
    0.08
    Activations Density 0.078%

    No Known Activations