© 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. 11692
    Prev
    Next
    INDEX
    Explanations

    material or scientific terms

    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
    vos
    -0.08
    amaan
    -0.07
    amen
    -0.07
     ì¢Į
    -0.07
    lasan
    -0.07
    æĹłåIJį
    -0.07
    -eslint
    -0.06
    utra
    -0.06
    amer
    -0.06
    íķĺìĭľ
    -0.06
    POSITIVE LOGITS
    —in
    0.09
    IGA
    0.08
    iglio
    0.08
    idge
    0.07
    본ë¶Ģ
    0.07
    åĥıåľ¨
    0.07
     Principe
    0.07
    ="#
    0.07
    avais
    0.07
    igan
    0.07
    Activations Density 0.209%

    No Known Activations