© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    phil, airborne, membrane, elongate, climbing, stationary

    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
    heti
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    å¤©æľº
    -0.08
    à¸ļาล
    -0.08
    leti
    -0.07
     Barros
    -0.07
    墩
    -0.07
    eni
    -0.07
    enia
    -0.07
    odoro
    -0.07
    POSITIVE LOGITS
    诸å¦Ĥ
    0.12
     items
    0.11
     things
    0.10
    items
    0.09
     ITEMS
    0.09
     Items
    0.09
    äºĭçī©
    0.08
    諸
    0.08
    çļĦäºĭçī©
    0.08
    Items
    0.08
    Activations Density 0.186%

    No Known Activations