© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    website links and names

    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
    çļĦåħ¨æĸ°
    -0.07
     heroic
    -0.07
    éĢļè¿ĩæŃ¤æ¬¡
    -0.07
    ÑĥÑĤÑĮ
    -0.07
    èĤ¥å¤§
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
     absolument
    -0.06
    ä¸ĭåIJĮ
    -0.06
    ĽĦ
    -0.06
    å¦ĤæĤ¨
    -0.06
    POSITIVE LOGITS
    ÙĪرÙĩا
    0.07
    è¾»
    0.07
    ezi
    0.07
    æĺĵ
    0.06
    quires
    0.06
     ÐŃÑĤ
    0.06
    gaard
    0.06
    Äħtek
    0.06
    divider
    0.06
    reso
    0.06
    Activations Density 0.013%

    No Known Activations