© 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. 16490
    Prev
    Next
    INDEX
    Explanations

    looping constructs

    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
    ä¸įæĹ©
    -0.08
    vers
    -0.07
     superf
    -0.07
    åĪ«ç¦»
    -0.07
    hani
    -0.07
    gin
    -0.07
    ä¸įæİī
    -0.07
    urig
    -0.07
    ipo
    -0.07
     Cath
    -0.07
    POSITIVE LOGITS
    ä¸ĭä¸Ģ次
    0.09
     Executes
    0.08
    åIJĦè¡Į
    0.08
    循çݯ
    0.08
     ceasefire
    0.07
    èĩªåĬ¨æݧåĪ¶
    0.07
     iteration
    0.07
    æŃ¥è¿Ľ
    0.07
     continuation
    0.07
     iterate
    0.07
    Activations Density 0.016%

    No Known Activations