© 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. 41219
    Prev
    Next
    INDEX
    Explanations

    polyester, polyether, polymer science

    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
    /apt
    -0.09
    丽èİİ
    -0.08
     atIndex
    -0.08
    ÑĤÑİ
    -0.08
    éŁŃ
    -0.08
    åĨ²æµª
    -0.07
    ÃĶI
    -0.07
    ierge
    -0.07
     truff
    -0.07
     Palmas
    -0.07
    POSITIVE LOGITS
    æ°ijæĶ¿å±Ģ
    0.07
    ç¼Ģ
    0.07
    building
    0.06
     building
    0.06
     remar
    0.06
     Poc
    0.06
     Zimmer
    0.06
    arkin
    0.06
    端起
    0.06
    .pg
    0.06
    Activations Density 0.029%

    No Known Activations