© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    demonstration or writing

    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
    elop
    -0.07
    elpers
    -0.07
    ä¸Ģæĭį
    -0.07
    åīįæµ·
    -0.07
    icama
    -0.06
    忧
    -0.06
     пеÑĢев
    -0.06
    ãĥ¬ãĥ¼ãĥī
    -0.06
     laying
    -0.06
    .logical
    -0.06
    POSITIVE LOGITS
     Demonstr
    0.09
     exempl
    0.09
     demonstrated
    0.09
    ixon
    0.08
     lesson
    0.08
    æĺ¯å¤ļä¹Ī
    0.08
     Illustrated
    0.08
    éĢļè¿ĩè¿Ļ个
    0.08
     demonstration
    0.08
     demonstr
    0.08
    Activations Density 0.359%

    No Known Activations