© 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. 24070
    Prev
    Next
    INDEX
    Explanations

    german "zur" or "wollte"

    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
    -0.10
    aras
    -0.07
    anean
    -0.07
     [
    -0.06
    ÃŃas
    -0.06
    å¹´ä¸ŃèĢĥ
    -0.06
     implying
    -0.06
    æıIJæĭĶ
    -0.06
    æĢİèĥ½
    -0.06
    ÙĪÙĨس
    -0.06
    POSITIVE LOGITS
    絡
    0.08
     ê°ĢëĬ¥íķĺë©°
    0.08
    gol
    0.07
    киÑĪе
    0.07
    ollo
    0.07
     crudo
    0.07
    åij±
    0.07
    éĢ»
    0.07
    绾
    0.07
    berat
    0.07
    Activations Density 0.024%

    No Known Activations