© 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. 65146
    Prev
    Next
    INDEX
    Explanations

    differential notation ($dx, ds, dt$)

    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
    Ł
    -0.09
    tk
    -0.09
    ами
    -0.09
    ness
    -0.08
    UDO
    -0.08
    麻麻
    -0.08
    tip
    -0.08
    ggi
    -0.08
    eau
    -0.08
    edException
    -0.08
    POSITIVE LOGITS
    Ùĩ
    0.10
    as
    0.07
    u
    0.07
    asian
    0.07
    ä¸įå®ĮçļĦ
    0.07
    ìĦľ
    0.07
    /dr
    0.06
    ש×ķת
    0.06
    да
    0.06
     selben
    0.06
    Activations Density 0.004%

    No Known Activations