© 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. 60687
    Prev
    Next
    INDEX
    Explanations

    special characters and 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
     thereby
    -0.08
    åĽłæŃ¤åľ¨
    -0.07
    ä»İèĢĮ
    -0.07
    æį®æѤ
    -0.07
    -0.07
     Ñģобой
    -0.07
    åľ¨è¿Ļä¸Ģ
    -0.07
    åľ¨è¿Ļ
    -0.06
     latter
    -0.06
    ä½Ĩ并ä¸į
    -0.06
    POSITIVE LOGITS
    ضاÙĨ
    0.09
    iaux
    0.09
    idaÄĩ
    0.08
    身临åħ¶å¢ĥ
    0.08
    urat
    0.08
    ieurs
    0.08
    &,
    0.08
    ,!
    0.08
    pell
    0.08
    åĴ³åĴ³
    0.08
    Activations Density 0.049%

    No Known Activations