© 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. 62339
    Prev
    Next
    INDEX
    Explanations

    table formatting characters

    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
    涤
    -0.08
    TED
    -0.07
    ĵ
    -0.07
    มà¸Ļ
    -0.07
    ews
    -0.07
    dock
    -0.07
    èĢĮä½ľä¸º
    -0.07
    าà¸ĩ
    -0.07
    çļĦ强大
    -0.07
     TF
    -0.07
    POSITIVE LOGITS
    éĢĤ
    0.07
    áginas
    0.07
    è¼
    0.07
    biot
    0.07
    ä¹ī
    0.06
    æľ
    0.06
    ynchronized
    0.06
    åıĪ好
    0.06
    quot
    0.06
    Balancer
    0.06
    Activations Density 0.003%

    No Known Activations