© 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. 50724
    Prev
    Next
    INDEX
    Explanations

    union members, table-row, bond, WebSocket, cluster, blast, processing, PK

    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
    çĩĥ
    -0.07
    åĨī
    -0.07
    baru
    -0.07
    åıĸ
    -0.07
    éĻĨ
    -0.06
    ä¸ªå·¥ä½ľ
    -0.06
    èµ°èµ°
    -0.06
    iria
    -0.06
    山海
    -0.06
    æľĢæĸ°ç«łèĬĤ
    -0.06
    POSITIVE LOGITS
     обл
    0.07
    çļĦä¸Ģåijĺ
    0.07
    ÏĢλα
    0.07
    åıĮèĥŀèĥİ
    0.07
    edList
    0.07
    avar
    0.07
    两çĶ¨
    0.07
    èĩªå·±åĴĮ
    0.07
    iosk
    0.07
    åĪĢåŃIJ
    0.07
    Activations Density 0.003%

    No Known Activations