© 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. 56575
    Prev
    Next
    INDEX
    Explanations

    averages and norms

    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
    积æŀģè´¡çĮ®
    -0.08
    Ñģпи
    -0.08
    翻转
    -0.08
    æŃ£åıį
    -0.08
    moth
    -0.08
    èĤ¡ä¸ľåıĬ
    -0.08
    è²¢çĮ®
    -0.07
     sever
    -0.07
    odel
    -0.07
    моÑĢ
    -0.07
    POSITIVE LOGITS
    å¹³åĿĩ
    0.10
     averages
    0.10
     median
    0.10
    median
    0.10
     avg
    0.09
    mean
    0.09
     mean
    0.09
    Median
    0.09
     average
    0.09
    å¹³åĿĩåĢ¼
    0.09
    Activations Density 0.005%

    No Known Activations