© 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. 39509
    Prev
    Next
    INDEX
    Explanations

    non- prefix

    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
     Whilst
    -0.20
    Whilst
    -0.20
     whilst
    -0.18
    åģļ为
    -0.15
     amongst
    -0.14
    综åIJĪçĹĩ
    -0.14
    åĩºæĿ¥ãĤĭ
    -0.13
    水份
    -0.13
     ÑĤеÑĩении
    -0.13
     Firstly
    -0.12
    POSITIVE LOGITS
    ãģķãģ¾ãģĸãģ¾ãģª
    0.12
    oward
    0.11
     nond
    0.11
    —and
    0.10
    é»ı
    0.10
     mithilfe
    0.10
     toward
    0.10
    åĪ¶è®¢
    0.10
    ä¸ĢçĤ¹åĦ¿
    0.10
    ologic
    0.10
    Activations Density 2.620%

    No Known Activations