© 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. 26176
    Prev
    Next
    INDEX
    Explanations

    German words and phrases

    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
    å¹´å§ĭ
    -0.09
    ResourceManager
    -0.09
    è°ģæĿ¥
    -0.08
    פ×ķת
    -0.08
    ingly
    -0.08
    nameof
    -0.07
     Postar
    -0.07
    åľ¨å¿ħ
    -0.07
    å¾ĭå·±
    -0.07
    çļĦ责任
    -0.07
    POSITIVE LOGITS
    æĤī
    0.08
    Õ¡Õ®
    0.07
    itive
    0.06
    ör
    0.06
    欧洲çļĦ
    0.06
    urf
    0.06
    ail
    0.06
     wer
    0.06
    ÑĥÑģÑĤ
    0.06
    ails
    0.06
    Activations Density 0.002%

    No Known Activations