© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    separate variables, multiplicative interaction, product, independence

    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
    кÑĤи
    -0.08
    psilon
    -0.08
    _DST
    -0.07
    髦
    -0.07
    olib
    -0.07
    éĿ¢çĽ®
    -0.07
    à¸Ĺาย
    -0.07
     rum
    -0.07
    _submission
    -0.07
    æµģè¡Ģ
    -0.07
    POSITIVE LOGITS
    çĭ¬ç«ĭæĢ§
    0.10
    çĭ¬ç«ĭçļĦ
    0.10
     separ
    0.10
    çĭ¬ç«ĭ
    0.10
     independent
    0.09
     Independence
    0.09
     independence
    0.09
     independently
    0.08
    Independent
    0.08
     separately
    0.08
    Activations Density 0.013%

    No Known Activations