© 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. 33710
    Prev
    Next
    INDEX
    Explanations

    alternatively, or, also, way, addition

    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
    åģĩå®ļ
    -0.07
    åIJŀ
    -0.07
     presumably
    -0.07
    åľ¨éĢĻ裡
    -0.07
    秫
    -0.07
    zn
    -0.07
    é¦ĸåħĪéľĢè¦ģ
    -0.07
    åħ¸
    -0.06
    zna
    -0.06
     pauta
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    ä¹Łåı¯ä»¥åľ¨
    0.08
    +:
    0.07
    çĽĸä¸ĸ
    0.07
    å°ĨæѤ
    0.07
    æıIJä¾ĽæĽ´
    0.07
    imagem
    0.07
     alternatively
    0.07
    ItemAt
    0.07
     esp
    0.07
    Activations Density 0.006%

    No Known Activations