© 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. 56497
    Prev
    Next
    INDEX
    Explanations

    positive and negative opposition

    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
    ä½Ĩèĩ³å°ij
    -0.07
    bund
    -0.07
    aving
    -0.07
    ®
    -0.07
    नà¥įन
    -0.07
    wirtschaft
    -0.07
     ζη
    -0.07
     cintura
    -0.07
    urat
    -0.07
    öss
    -0.07
    POSITIVE LOGITS
    volent
    0.07
    .createFrom
    0.07
    adb
    0.07
    umpa
    0.07
    æŃ£åĢ¼
    0.07
    çļĦè¯Ŀ
    0.07
    ugn
    0.07
    positive
    0.06
    IDO
    0.06
    èī¯èį¯
    0.06
    Activations Density 0.002%

    No Known Activations