© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    seeking or stating facts

    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
    sic
    -0.09
    edor
    -0.08
    ä¼Ĺ
    -0.07
    Õ¡Õ¿
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
    Ø©
    -0.06
    éĢļè¿ĩ以ä¸Ĭ
    -0.06
    due
    -0.06
     sole
    -0.06
     presumably
    -0.06
    POSITIVE LOGITS
    adÃŃ
    0.08
     surprisingly
    0.08
    ]|[
    0.07
    wab
    0.07
    udid
    0.07
     [âĢ¦]
    0.07
    ç¢
    0.07
    åľ°æľĽçĿĢ
    0.07
    |RF
    0.07
     [âĢ¦
    0.07
    Activations Density 0.039%

    No Known Activations