© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    `ll` followed by `ll`

    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
    SetUp
    -0.08
    takt
    -0.07
    .tex
    -0.07
    åĨ²åIJij
    -0.06
    tement
    -0.06
    ãĥŃãĤ¹
    -0.06
    è´¥
    -0.06
    UGIN
    -0.06
    ugna
    -0.06
    أس
    -0.06
    POSITIVE LOGITS
    onn
    0.07
    Pil
    0.07
    ovable
    0.07
    igy
    0.07
    ª
    0.07
    åĪĪ
    0.07
    éķ¿çļĦ
    0.06
    оÑģÑĤ
    0.06
    ç¥ŀä»Ļ
    0.06
    /sidebar
    0.06
    Activations Density 0.306%

    No Known Activations