© 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. 20925
    Prev
    Next
    INDEX
    Explanations

    file names and properties

    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
    çĺ©
    -0.09
    çIJµ
    -0.09
     banj
    -0.08
    ниÑĤи
    -0.08
    .interpolate
    -0.08
    åIJİæĿ¥åıĪ
    -0.08
     Bestseller
    -0.07
    _TOO
    -0.07
     بعدÙĩ
    -0.07
    rega
    -0.07
    POSITIVE LOGITS
     Claw
    0.06
    ä¸įçĿĢ
    0.06
     Council
    0.06
    C
    0.06
    /
    0.06
    aci
    0.06
    éķ¿çĶŁ
    0.05
    иÑģÑĮ
    0.05
    ito
    0.05
     Tấn
    0.05
    Activations Density 0.090%

    No Known Activations