© 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. 62772
    Prev
    Next
    INDEX
    Explanations

    Americans in shifts

    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
    ersen
    -0.07
    YTE
    -0.07
    il
    -0.07
    imb
    -0.07
    ek
    -0.06
    yk
    -0.06
    йн
    -0.06
    èĶļèĵĿ
    -0.06
    ik
    -0.06
    yka
    -0.06
    POSITIVE LOGITS
     **.**
    0.08
    ×ĵת
    0.07
    vvm
    0.07
    isy
    0.07
    å®
    0.07
    weiler
    0.07
     omas
    0.07
     **:**
    0.07
    ruck
    0.07
    Printf
    0.07
    Activations Density 0.002%

    No Known Activations