© 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. 47304
    Prev
    Next
    INDEX
    Explanations

    polymer, material, particles

    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
    å®¹é¢ľ
    -0.07
    å±±ä¸Ń
    -0.07
     version
    -0.07
    regor
    -0.07
    满æĢĢ
    -0.07
    èĩ³å°Ĭ
    -0.07
     dash
    -0.06
    æ¹ĸ滨
    -0.06
     perl
    -0.06
    æ´»äºĨ
    -0.06
    POSITIVE LOGITS
     Dek
    0.08
    åĴĭ
    0.07
    æĤ¬
    0.07
    ahi
    0.07
    menta
    0.07
    ammer
    0.06
    empat
    0.06
     Mora
    0.06
    è¿Ļä¸ī
    0.06
     поÑĢа
    0.06
    Activations Density 0.086%

    No Known Activations