© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46579
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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
    azon
    -0.08
    å¼Ĥ
    -0.07
    yz
    -0.07
     reluctantly
    -0.07
    ä¾Ŀ
    -0.06
    uno
    -0.06
     sp
    -0.06
     silently
    -0.06
     literally
    -0.06
    put
    -0.06
    POSITIVE LOGITS
    errupt
    0.10
    ä¸Ģåıĺ
    0.08
    ä»Ģä¹Īäºĭæĥħ
    0.07
    ס×Ķ
    0.07
    trand
    0.07
    ãģªãģį
    0.07
    orter
    0.07
    æīĵåĵį
    0.07
    éļİ
    0.07
    æĢĢä¸Ń
    0.07
    Activations Density 0.001%

    No Known Activations