© 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. 42878
    Prev
    Next
    INDEX
    Explanations

    chip, port, texture, network, center, group

    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
    æĪĸåħ¶
    -0.07
    åıĬåħ¶
    -0.07
    åľ¨åħ¨
    -0.06
    attet
    -0.06
    iphery
    -0.06
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    -0.06
    à¸ĩ
    -0.06
    åıĬåĪ©æģ¯
    -0.06
    avera
    -0.06
    vena
    -0.06
    POSITIVE LOGITS
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.11
     ulang
    0.09
     them
    0.09
    thesize
    0.09
     ourselves
    0.09
    æĪijåIJ§
    0.08
    amalla
    0.08
    å®ĥ以
    0.08
    /stretch
    0.08
    æķ´ä¸ª
    0.08
    Activations Density 0.759%

    No Known Activations