© 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. 43941
    Prev
    Next
    INDEX
    Explanations

    on-base percentage

    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
    idio
    -0.07
    arra
    -0.07
    à¸Ļา
    -0.07
    bero
    -0.07
    кона
    -0.07
    InitialState
    -0.07
    å¤ļå¤ļ
    -0.07
    å¸¸åľ¨
    -0.07
     Pepper
    -0.07
    parison
    -0.07
    POSITIVE LOGITS
    åĮħæĭ¬äºĨ
    0.11
    åIJĪ计
    0.11
     excluding
    0.10
    excluding
    0.10
     inclusive
    0.09
    åĮħæĭ¬
    0.09
     encompasses
    0.09
     exclude
    0.09
     excludes
    0.09
     total
    0.09
    Activations Density 0.070%

    No Known Activations