© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    citations preceded by @

    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
    约èĢĮåIJĮ
    -0.13
     nhau
    -0.11
    åIJĦèĩªçļĦ
    -0.11
     themselves
    -0.11
    å½¼æѤ
    -0.11
    å½¼æѤçļĦ
    -0.10
     eds
    -0.10
    åIJĦèĩª
    -0.10
     sami
    -0.09
    åIJĪåĬĽ
    -0.09
    POSITIVE LOGITS
     himself
    0.13
    çĭ¬
    0.12
    çį¨
    0.11
    çĭ¬èĩª
    0.11
    çĭ¬èĩªä¸Ģ人
    0.11
     solo
    0.11
    çį¨èĩª
    0.10
     alone
    0.09
     sozinho
    0.09
     íĺ¼ìŀIJ
    0.09
    Activations Density 0.238%

    No Known Activations