© 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. 17225
    Prev
    Next
    INDEX
    Explanations

    interrogated, asked, warn

    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
    åĽ¾æºIJ
    -0.11
    reon
    -0.09
    ÑİÑĢпÑĢи
    -0.09
    iated
    -0.09
    她表示
    -0.09
    èĢĮéĤ£äºĽ
    -0.09
    indsight
    -0.08
    ergestellt
    -0.08
    iou
    -0.08
    为äºĨ解åĨ³
    -0.08
    POSITIVE LOGITS
    çļĦæĺ¯
    0.11
    ega
    0.08
    ä¸įä¼ij
    0.08
    naires
    0.07
    بع
    0.07
     whether
    0.07
    how
    0.07
    «
    0.07
    éĹ®æĪij
    0.07
    çļĦæĺ¯ä¸Ģ个
    0.07
    Activations Density 0.001%

    No Known Activations