© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63145
    Prev
    Next
    INDEX
    Explanations

    Na/K transport/ATPase

    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
    orial
    -0.07
    aign
    -0.07
    adf
    -0.07
    oroz
    -0.07
    agraph
    -0.07
     inher
    -0.06
    ugu
    -0.06
    egu
    -0.06
    åħĭæľįåĽ°éļ¾
    -0.06
    è¸ı
    -0.06
    POSITIVE LOGITS
    ç»´æĮģ
    0.08
    issons
    0.08
    åIJijå¤ĸ
    0.08
    åįĵ
    0.08
    å¾Ģå¤ĸ
    0.08
    åĥįãģį
    0.08
    马é¾Ļ
    0.07
     auÃŁen
    0.07
    åĤ¨åŃĺ
    0.07
    anzi
    0.07
    Activations Density 0.019%

    No Known Activations