© 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. 43809
    Prev
    Next
    INDEX
    Explanations

    love and loss

    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
    津津
    -0.07
    essi
    -0.07
    ToString
    -0.07
    vell
    -0.07
    æķ·
    -0.06
    inius
    -0.06
    èĢģèĢģå®ŀ
    -0.06
    éĢĬ
    -0.06
    说å®ŀè¯Ŀ
    -0.06
    eval
    -0.06
    POSITIVE LOGITS
    æŃĮè¯į
    0.07
    è¯ķåIJ¬
    0.07
    бÑĢе
    0.07
    èĽ¹
    0.07
    ä½ľè¯į
    0.07
    羯
    0.07
    à¸ģล
    0.07
    翻天è¦Ĩ
    0.07
    æĭħ
    0.07
    (SIG
    0.07
    Activations Density 0.159%

    No Known Activations