© 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. 9952
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols

    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
    åĽĽä¸ªäºº
    -0.08
    heed
    -0.07
    åĽĽçĤ¹
    -0.07
    ÅĻi
    -0.07
    åĽĽæĿ¡
    -0.07
    ÑĤÑĢ
    -0.07
    çļĦåĽĽ
    -0.06
    æĿİåħĭ
    -0.06
    icer
    -0.06
    .${
    -0.06
    POSITIVE LOGITS
    以ä¸Ĭæĺ¯
    0.08
    以ä¸Ĭ
    0.08
    indent
    0.07
    宣
    0.07
    çŃīçŃī
    0.07
    InstanceOf
    0.07
     miscellaneous
    0.07
    åĤĻèĢĥ
    0.06
    ÑĦина
    0.06
     zest
    0.06
    Activations Density 0.100%

    No Known Activations