© 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. 64330
    Prev
    Next
    INDEX
    Explanations

    encyclopedia of

    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
    terra
    -0.07
    ifah
    -0.07
    æľ¬ç¯ĩæĸĩç«ł
    -0.07
    å¥½ä¸ľè¥¿
    -0.07
    aglia
    -0.06
    被çĽĹ
    -0.06
    à¹Ģà¸Ĺศ
    -0.06
    æĻļä¸ĬçļĦ
    -0.06
    çļĦä¸ĢäºĽ
    -0.06
    seven
    -0.06
    POSITIVE LOGITS
    eras
    0.07
    HLT
    0.07
    orable
    0.07
    eliness
    0.07
    ably
    0.07
    alas
    0.07
     setFrame
    0.07
     Höchst
    0.07
    ered
    0.06
     datap
    0.06
    Activations Density 0.002%

    No Known Activations