© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16862
    Prev
    Next
    INDEX
    Explanations

    international documents and identification

    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
    åĨ¤
    -0.07
    éŃħ
    -0.07
    macher
    -0.06
    -links
    -0.06
    æ®·
    -0.06
    links
    -0.06
    ç¥Ī
    -0.06
    éľĩ
    -0.06
    ä¸ĢæĬ¹
    -0.06
     links
    -0.06
    POSITIVE LOGITS
    è¿Ļæīįæĺ¯
    0.14
    æīįæĺ¯
    0.14
    æīį对
    0.13
    æīįæĺ¯çľŁæŃ£çļĦ
    0.12
    æīįæĺ¯æľĢ
    0.11
    à¹Ģà¸Ľà¹ĩà¸Ļหลัà¸ģ
    0.10
    主导
    0.10
    为主导
    0.10
    çĭ¬ç«ĭ
    0.09
    æīįèĥ½çľŁæŃ£
    0.09
    Activations Density 0.023%

    No Known Activations