© 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. 58142
    Prev
    Next
    INDEX
    Explanations

    qualifying adjectives for nouns

    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
    rosso
    -0.07
    åľ°
    -0.07
    类似äºİ
    -0.07
     similar
    -0.07
     خز
    -0.06
    æľĽè¿ľéķľ
    -0.06
     âĸª
    -0.06
    impin
    -0.06
    ç¥ī
    -0.06
    ****
    -0.06
    POSITIVE LOGITS
     hoá
    0.09
    igmatic
    0.07
    .bind
    0.07
    oppi
    0.07
    两类
    0.07
     yearly
    0.07
    ãģ¯ãģļ
    0.07
    è¡©
    0.07
    į
    0.07
     ancak
    0.07
    Activations Density 0.003%

    No Known Activations