© 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. 58339
    Prev
    Next
    INDEX
    Explanations

    bikes, API, BBQ, suppliers

    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
    çĤ¹åĩ»ä¸Ĭæĸ¹
    -0.07
    ãģµãģĨ
    -0.06
    mland
    -0.06
    ça
    -0.06
     Lemb
    -0.06
    ìĿį
    -0.06
    ãģļãģ¤
    -0.06
    ampton
    -0.06
    å§Ĩæĸ¯
    -0.06
    usu
    -0.06
    POSITIVE LOGITS
    ä¹Łå¥½
    0.10
     bowiem
    0.10
    ãĢģ
    0.10
    ä¹Łç½¢
    0.08
     enim
    0.08
    æĢ§åĴĮ
    0.08
    ablish
    0.07
     totiž
    0.07
     ugyanis
    0.07
    -,
    0.07
    Activations Density 1.060%

    No Known Activations