© 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. 31896
    Prev
    Next
    INDEX
    Explanations

    Germany and German

    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
     Karachi
    -0.07
     Rodrigues
    -0.07
    eir
    -0.07
     Conor
    -0.07
    Configurer
    -0.07
     Pereira
    -0.06
    Laugh
    -0.06
    ä¸ĢåĪ»
    -0.06
     Rodrig
    -0.06
    衣裳
    -0.06
    POSITIVE LOGITS
    å¾·åĽ½
    0.12
    åľ¨å¾·åĽ½
    0.12
    å¾·è¯Ń
    0.11
    æħķå°¼é»ij
    0.11
    å¾·åľĭ
    0.11
     Ø£ÙĦÙħاÙĨÙĬا
    0.11
     ëıħìĿ¼
    0.11
     nrw
    0.11
     köln
    0.10
    å¾·åĽ½çļĦ
    0.10
    Activations Density 0.604%

    No Known Activations