© 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. 64292
    Prev
    Next
    INDEX
    Explanations

    asking for or providing answers

    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
    å®°
    -0.07
    inger
    -0.07
    æľī个
    -0.06
    å¼ĢæĶ¯
    -0.06
    rier
    -0.06
    æĬ¥å¯¼
    -0.06
    èĢĥé¢ĺ
    -0.06
     пÑĢиÑģ
    -0.06
     lately
    -0.06
    iec
    -0.06
    POSITIVE LOGITS
    лана
    0.09
    åĴĮæݨ广
    0.08
    odom
    0.08
    å¯¹åľ¨
    0.08
    клада
    0.08
    /result
    0.07
     berupa
    0.07
    answers
    0.07
    yty
    0.07
    nder
    0.07
    Activations Density 0.041%

    No Known Activations