© 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. 23344
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    ekar
    -0.07
    ék
    -0.06
    atter
    -0.06
    anger
    -0.06
    anc
    -0.06
    æī¦
    -0.06
     Globe
    -0.06
     Bens
    -0.06
    çݰ代åĮĸ建设
    -0.06
    ^
    -0.06
    POSITIVE LOGITS
    ACY
    0.08
    ×Ļ׳×ķ
    0.07
    inum
    0.07
    anat
    0.07
    urang
    0.07
     Ëĩ
    0.07
    æĨ
    0.07
    Ä©a
    0.07
    å·®ä¸į
    0.07
    iday
    0.07
    Activations Density 0.006%

    No Known Activations