© 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. 13056
    Prev
    Next
    INDEX
    Explanations

    sayings, quotes, mottos

    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
    <|box_end|>
    -0.10
    èĤĮ
    -0.09
    ptype
    -0.08
    lise
    -0.08
     Detalhes
    -0.08
     Pubbl
    -0.08
     [+]
    -0.08
    æķħäºĭæĥħ
    -0.08
    ervo
    -0.08
    æķħäºĭæĥħèĬĤ
    -0.08
    POSITIVE LOGITS
    éĤ£åı¥
    0.13
     motto
    0.13
    çļĦä¸Ģåı¥è¯Ŀ
    0.13
    åIJįè¨Ģ
    0.13
    äºĨä¸Ģåı¥
    0.13
    æł¼è¨Ģ
    0.13
     quote
    0.12
    èѦåı¥
    0.12
     quoted
    0.12
    è¿Ļåı¥è¯Ŀ
    0.12
    Activations Density 0.233%

    No Known Activations