© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    comma delimited or separated

    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
    ÙħÙĨد
    -0.08
    imenta
    -0.08
    ر
    -0.08
    erton
    -0.07
    mr
    -0.07
    inge
    -0.07
    ½
    -0.07
    amer
    -0.07
    oris
    -0.07
    èĥ½æľī
    -0.07
    POSITIVE LOGITS
    azen
    0.09
    és
    0.08
    ================================================================
    0.08
    -shaped
    0.07
    ahir
    0.07
    elsea
    0.07
    мино
    0.07
    æķijåij½
    0.07
    ette
    0.07
    ified
    0.06
    Activations Density 0.031%

    No Known Activations