© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    negation words 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
     Pró
    -0.07
    ä¸įå¦Ļ
    -0.07
     trac
    -0.06
     Kö
    -0.06
    esm
    -0.06
    umd
    -0.06
    IMO
    -0.06
    æĤ²æ¬¢
    -0.06
    çek
    -0.06
    urm
    -0.06
    POSITIVE LOGITS
     phủ
    0.10
     neg
    0.10
    éĻ¤æģ¶
    0.09
    .neg
    0.09
    åIJ¦å®ļ
    0.09
    opsis
    0.08
     negate
    0.08
    -negative
    0.08
    Dims
    0.08
     ¬
    0.07
    Activations Density 0.014%

    No Known Activations