© 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. 14252
    Prev
    Next
    INDEX
    Explanations

    glycan or carbohydrate suffixes -ide, -yl

    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
    èĥ¤
    -0.08
     plunged
    -0.08
    å²±
    -0.08
     Surya
    -0.08
    eks
    -0.07
    çijľ
    -0.07
     plunge
    -0.07
     Marin
    -0.07
    太éĺ³èĥ½
    -0.07
    é¢Ħå¤ĩ
    -0.07
    POSITIVE LOGITS
    éĻĦçĿĢ
    0.08
     attach
    0.08
    uster
    0.08
    .decorate
    0.08
    _attachment
    0.08
     attached
    0.08
    ç³ĸ
    0.08
    é»ı
    0.08
     attachment
    0.08
    ä»ĭ
    0.08
    Activations Density 0.111%

    No Known Activations