© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    's text or 'is' text

    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
    麹
    -0.08
    ä½ļåIJį
    -0.08
    ielt
    -0.07
    forsch
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    à¸Ńำà¸Ļวย
    -0.07
    olvers
    -0.07
    çª
    -0.07
     rése
    -0.07
    apos
    -0.07
    POSITIVE LOGITS
    æĢİ麼
    0.07
    æĶ¾ä¸Ĭ
    0.07
    壮
    0.06
    mos
    0.06
     STEP
    0.06
    åľ¨æĦı
    0.06
     voc
    0.06
    ×¢×ķת
    0.06
     step
    0.06
    ÑĩÑijÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations