© 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. 56677
    Prev
    Next
    INDEX
    Explanations

    months, programming, and scientific terms

    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
    ило
    -0.06
    elda
    -0.06
    æĸ¹çķ¥
    -0.06
     ÑģколÑĮ
    -0.06
    çī¹å¾ģæĺ¯
    -0.05
     Nov
    -0.05
    .cv
    -0.05
    gon
    -0.05
    æĢĿæºIJ
    -0.05
    оÑģÑĤо
    -0.05
    POSITIVE LOGITS
    _EXTENSIONS
    0.09
    ãĥ¼ãĥĦ
    0.08
    otime
    0.08
    utus
    0.08
    -urlencoded
    0.08
    мли
    0.08
    ableView
    0.07
    μί
    0.07
    tica
    0.07
     Uncategorized
    0.07
    Activations Density 0.018%

    No Known Activations