© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 22925
    Prev
    Next
    INDEX
    Explanations

    parenthetical 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
    ãĢįï¼Ī
    -0.08
     ï¼Ī
    -0.08
    ï¼Ī
    -0.07
    ï¼ģï¼Ī
    -0.07
    ãĢĤï¼Ī
    -0.07
    ãĢıï¼Ī
    -0.07
    icho
    -0.07
    (?)
    -0.06
     ("
    -0.06
    å
    -0.06
    POSITIVE LOGITS
    ï¼Łï¼ī
    0.11
    â̦).
    0.10
     ...)
    0.10
    â̦),
    0.10
    »)
    0.09
    ..)
    0.09
    ++)
    0.09
    ?).
    0.09
    .),
    0.09
    â̦)
    0.09
    Activations Density 0.122%

    No Known Activations