© 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. 29423
    Prev
    Next
    INDEX
    Explanations

    app, startup, Germany, surgery, Bitcoin, Instagram

    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
     -
    -0.07
    endent
    -0.07
     (...)
    -0.07
     whopping
    -0.07
     [âĢ¦]
    -0.07
    ...
    -0.07
     Pokemon
    -0.07
    -
    -0.07
     ****
    -0.07
    æĤ¬æµ®
    -0.07
    POSITIVE LOGITS
    âĢij
    0.15
    .–
    0.08
    âĢ
    0.07
    îtes
    0.07
    该éķĩ
    0.07
    ’)
    0.07
    ÂŃing
    0.07
    è´Łè´£ç»Ħç»ĩ
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    婧
    0.07
    Activations Density 0.414%

    No Known Activations