© 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. 10404
    Prev
    Next
    INDEX
    Explanations

    dimer or heterodimer formation

    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
     lazy
    -0.08
    æĽ³
    -0.07
    ä¹ł
    -0.07
    shade
    -0.07
    lazy
    -0.07
     radi
    -0.07
    ser
    -0.06
    æĩĴ
    -0.06
     Dominion
    -0.06
    æĻ®æ£®
    -0.06
    POSITIVE LOGITS
    cker
    0.08
    apore
    0.08
    太ä»ĵ
    0.08
    çIJ³
    0.08
    åIJĮæĢ§
    0.08
    isky
    0.08
    mpp
    0.08
    åĩĿè¡Ģ
    0.08
     usp
    0.07
    stech
    0.07
    Activations Density 0.001%

    No Known Activations