© 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. 51163
    Prev
    Next
    INDEX
    Explanations

    compound words, phrases, names

    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
    cus
    -0.07
    ješ
    -0.07
    าย
    -0.07
    chied
    -0.07
    egger
    -0.07
    æĥŁä¸Ģ
    -0.07
    ä¸Ģåı·
    -0.07
    overe
    -0.07
    æľĢ令人
    -0.07
    .lambda
    -0.07
    POSITIVE LOGITS
    ç»ĦåIJĪ
    0.12
    çµĦåIJĪ
    0.10
     formed
    0.09
    çļĦç»ĦåIJĪ
    0.08
     compound
    0.08
     composto
    0.08
    çŁŃè¯Ń
    0.08
    å¤įåIJĪ
    0.08
     coined
    0.08
    åIJĪ
    0.08
    Activations Density 0.014%

    No Known Activations