© 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. 55593
    Prev
    Next
    INDEX
    Explanations

    conjugation; conjugacy; conjugation protein

    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
    abo
    -0.08
    Fel
    -0.07
     Fel
    -0.07
    _web
    -0.07
    _BINDING
    -0.07
    ãĤģãģ§
    -0.06
    uem
    -0.06
     meter
    -0.06
    occas
    -0.06
     hed
    -0.06
    POSITIVE LOGITS
    wirkung
    0.08
    çijŀæĭī
    0.08
    psilon
    0.07
    ilee
    0.07
    èĸ°
    0.07
     vuelta
    0.07
    .active
    0.07
    æ¼
    0.07
    ç®
    0.07
    è¼
    0.07
    Activations Density 0.002%

    No Known Activations