© 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. 57268
    Prev
    Next
    INDEX
    Explanations

    quotes and quotation marks

    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
    PEED
    -0.08
    mert
    -0.08
    andan
    -0.08
    prost
    -0.07
    äºĭæĪIJ
    -0.07
    oca
    -0.07
    atika
    -0.07
    åħį费注åĨĮ
    -0.07
    edic
    -0.07
    Ī¬
    -0.07
    POSITIVE LOGITS
    ÑģÑı
    0.08
    isan
    0.08
    ä¸į严
    0.08
     Mati
    0.07
    itchen
    0.07
    .semantic
    0.07
    _lengths
    0.07
    èIJ¥éĢłèī¯å¥½
    0.07
     cáºŃy
    0.07
    æĴĩ
    0.06
    Activations Density 0.054%

    No Known Activations