© 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. 24275
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    äºİæĺ¯ä»ĸ
    -0.08
    ä½ķçŃī
    -0.07
    è´£ç¼ĸ
    -0.07
    æīĢ以è¦ģ
    -0.07
    hton
    -0.07
    æĺ¥æĿ¥
    -0.07
    å¦ĤæѤä¸ĢæĿ¥
    -0.07
    aison
    -0.07
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
     Trev
    -0.07
    POSITIVE LOGITS
    der
    0.09
    دÙĩ
    0.08
    amani
    0.08
    spread
    0.08
    为éļ¾
    0.07
     albeit
    0.07
    klad
    0.07
    graph
    0.07
    odes
    0.07
    -archive
    0.07
    Activations Density 0.218%

    No Known Activations