© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15914
    Prev
    Next
    INDEX
    Explanations

    "there"

    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
    eenth
    -0.10
    oglio
    -0.09
    italia
    -0.09
    ег
    -0.08
    mier
    -0.08
    eira
    -0.08
    ucid
    -0.08
    à¥įल
    -0.08
    ingat
    -0.08
    auc
    -0.08
    POSITIVE LOGITS
    zelfde
    0.12
    hle
    0.11
    à¹ģหละ
    0.09
    ÑĩаÑģ
    0.09
    upon
    0.09
    oretical
    0.09
    段æŶéĹ´
    0.08
    Ŀ
    0.08
    ../../../
    0.08
    ÑĤи
    0.08
    Activations Density 0.020%

    No Known Activations