© 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. 57609
    Prev
    Next
    INDEX
    Explanations

    not working or unsuccessful

    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
    ennem
    -0.07
    otty
    -0.07
     diri
    -0.07
    ï¼Łï¼ī
    -0.07
    ign
    -0.07
    uisse
    -0.06
    ency
    -0.06
    iche
    -0.06
    unno
    -0.06
    utions
    -0.06
    POSITIVE LOGITS
    elh
    0.07
    iard
    0.07
    ayas
    0.07
    false
    0.07
    vero
    0.07
    ARTA
    0.07
    лед
    0.07
    קר
    0.06
    activex
    0.06
    ÑĢеб
    0.06
    Activations Density 0.004%

    No Known Activations