© 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. 24895
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    念
    -0.08
    _fn
    -0.07
     sö
    -0.07
    _MAIN
    -0.06
    olon
    -0.06
    æĪĸçĶ±
    -0.06
     mini
    -0.06
    è·Ł
    -0.06
    URN
    -0.06
    izo
    -0.06
    POSITIVE LOGITS
    andez
    0.08
    Ñħол
    0.08
    à¹ģà¸ķà¹Ī
    0.08
    andex
    0.08
    вле
    0.08
    pst
    0.07
    .clock
    0.07
    rell
    0.07
    åį´æľī
    0.07
    åĮ£
    0.07
    Activations Density 0.199%

    No Known Activations