© 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. 22204
    Prev
    Next
    INDEX
    Explanations

    polymer conformation stretch

    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
    åĩ¿
    -0.08
    arif
    -0.07
     Cricket
    -0.07
    æĸ©
    -0.07
    ç«
    -0.07
     fool
    -0.07
     гла
    -0.07
    à¹Ģà¸Īาะ
    -0.07
    antry
    -0.06
    udz
    -0.06
    POSITIVE LOGITS
    ä¼¸çĽ´
    0.09
     polymer
    0.09
     stretched
    0.08
    bundle
    0.08
    伸å±ķ
    0.08
    Stretch
    0.08
    èĪĴå±ķ
    0.08
     бÑĢо
    0.08
     Lange
    0.08
    retched
    0.08
    Activations Density 0.011%

    No Known Activations