© 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. 50484
    Prev
    Next
    INDEX
    Explanations

    non-latin characters

    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°¼äºŀ
    -0.08
    ļľ
    -0.08
    -
    -0.08
    ä»°
    -0.07
    æµĵåİļ
    -0.07
    åĭĥåĭĥ
    -0.07
    ulton
    -0.07
    สมัà¸Ħร
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.06
    å¾Īéļ¾
    -0.06
    POSITIVE LOGITS
    ¹
    0.10
    ¨
    0.10
    ł
    0.09
    ģ
    0.09
    µ
    0.09
    §
    0.09
    º
    0.08
    ³
    0.08
    ¥
    0.08
    ij
    0.08
    Activations Density 0.009%

    No Known Activations