© 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. 65458
    Prev
    Next
    INDEX
    Explanations

    nickel, lead, iron, metal, electrode

    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
    çĭĤæļ´
    -0.07
     wym
    -0.07
     Spicer
    -0.07
     menek
    -0.07
    ows
    -0.07
    个æ¡Ī
    -0.07
    æĸ
    -0.07
    失æݧ
    -0.07
    eluk
    -0.07
     tents
    -0.06
    POSITIVE LOGITS
    Tho
    0.08
    æľºèĬ¯
    0.07
    äºĮ线
    0.07
     pac
    0.07
    fond
    0.07
    æݥ线
    0.07
    igli
    0.07
    odate
    0.07
    stro
    0.07
    ocal
    0.06
    Activations Density 0.003%

    No Known Activations