© 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. 47951
    Prev
    Next
    INDEX
    Explanations

    labor productivity growth

    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
    ed
    -0.15
    ness
    -0.12
    jenigen
    -0.10
    edr
    -0.10
    lore
    -0.10
    ات
    -0.10
    yard
    -0.09
    ะ
    -0.09
    assel
    -0.09
    s
    -0.09
    POSITIVE LOGITS
    ä½İä¸ĭ
    0.08
    giene
    0.08
    ktan
    0.08
    ehme
    0.07
    untime
    0.07
    OptionsMenu
    0.07
    plevel
    0.07
    عا
    0.07
    åģ¥åº·ç½ij
    0.07
    æŃĩå°Ķ
    0.07
    Activations Density 0.004%

    No Known Activations