© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10891
    Prev
    Next
    INDEX
    Explanations

    Johns Hopkins Children's

    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
    esus
    -0.07
    ukan
    -0.07
    gom
    -0.07
    eso
    -0.07
    èĬĻèĵī
    -0.07
    lukan
    -0.07
    o
    -0.07
    ове
    -0.06
    æĥħæ·±
    -0.06
    esa
    -0.06
    POSITIVE LOGITS
    zec
    0.08
    å«£
    0.07
    idth
    0.07
    æĿĥè¯ģ
    0.07
    arent
    0.07
    èıħ
    0.07
    conte
    0.07
    aren
    0.07
    çIJ¥
    0.07
    aley
    0.07
    Activations Density 0.048%

    No Known Activations