© 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. 21250
    Prev
    Next
    INDEX
    Explanations

    ER positive

    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
    (Call
    -0.07
    sait
    -0.07
    ikat
    -0.07
     íĻķ
    -0.06
    ESIS
    -0.06
    å½Ĵ
    -0.06
    gl
    -0.06
    ULO
    -0.06
    并ä¸įæĺ¯
    -0.06
    ели
    -0.06
    POSITIVE LOGITS
    è¿ĽèĢĮ
    0.09
    ä»İèĢĮ
    0.08
    éĢ²èĢĮ
    0.08
    ä¹Łå°±ä¸į
    0.08
    å¾ŀèĢĮ
    0.08
    ä»İèĢĮ使
    0.08
    缸åħ³æ³ķå¾ĭ责任
    0.08
     بدÙĪرÙĩ
    0.07
    ä¹ŁæĪIJ为äºĨ
    0.07
    ä¹ŁæĪIJ为
    0.07
    Activations Density 0.725%

    No Known Activations