© 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. 26157
    Prev
    Next
    INDEX
    Explanations

    German place names and entities

    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
     vite
    -0.07
    νομ
    -0.07
    ä¾Ŀæ³ķé¡»ç»ı
    -0.07
    uib
    -0.07
    ieh
    -0.07
     [âĢ¦]
    -0.06
    æĶ¾åľ¨ç¬¬ä¸Ģä½į
    -0.06
    iefe
    -0.06
     ................
    -0.06
    æĢ»å±Ģ
    -0.06
    POSITIVE LOGITS
    æ¸
    0.07
    ãĤ¸ãĥ³
    0.07
    erat
    0.07
    Dispatch
    0.07
    olina
    0.06
    æļ§
    0.06
     пÑĢиÑģ
    0.06
     Responsible
    0.06
    ists
    0.06
    stdClass
    0.06
    Activations Density 0.072%

    No Known Activations