© 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. 27968
    Prev
    Next
    INDEX
    Explanations

    team or teams followed by specific noun

    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
    ëĤĺë§Ī
    -0.09
    inach
    -0.08
    mero
    -0.08
    俱ä¹IJéĥ¨
    -0.08
     haired
    -0.08
    atti
    -0.08
    -speaking
    -0.08
     окÑĢÑĥжаÑİÑīей
    -0.07
    fter
    -0.07
    çĦ¶æĺ¯
    -0.07
    POSITIVE LOGITS
    ÙĨائ
    0.08
    yard
    0.08
    人马
    0.08
    stead
    0.08
    دار
    0.08
    mates
    0.07
    otle
    0.07
    åijĺçļĦ
    0.07
    yards
    0.07
    zinho
    0.07
    Activations Density 0.144%

    No Known Activations