© 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. 57815
    Prev
    Next
    INDEX
    Explanations

    metallophones, Explorer, pandas, AtPath, Adventures

    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
    çĮ¾
    -0.07
     reckon
    -0.07
    éĺµ
    -0.06
    çݺ
    -0.06
    åıĮæĸ¹åľ¨
    -0.06
    parte
    -0.06
    ä¸Ģ个æĺ¯
    -0.06
    ä»İ头
    -0.06
    .Scheme
    -0.06
    让广大
    -0.06
    POSITIVE LOGITS
    velt
    0.08
    odesk
    0.07
    AtPath
    0.07
    ARED
    0.07
    ivable
    0.07
    adera
    0.07
     зака
    0.07
    رب
    0.07
    atkan
    0.07
    nden
    0.06
    Activations Density 0.327%

    No Known Activations