© 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. 45806
    Prev
    Next
    INDEX
    Explanations

    word completion after punctuation

    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
    earch
    -0.05
    ¯
    -0.05
    uve
    -0.05
    ignon
    -0.04
    lector
    -0.04
    ugat
    -0.04
    uds
    -0.04
    ูล
    -0.04
    è¶Ĭä½İ
    -0.04
    angi
    -0.04
    POSITIVE LOGITS
    asseur
    0.07
    lipp
    0.07
    该楼å±Ĥçĸijä¼¼è¿Ŀè§Ħå·²è¢«ç³»ç»ŁæĬĺåıł
    0.07
    rrha
    0.07
    pah
    0.07
    UPER
    0.07
    åIJij被åijĬ
    0.07
    说æĿ¥
    0.06
    ordes
    0.06
    amanya
    0.06
    Activations Density 1.307%

    No Known Activations