© 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. 9646
    Prev
    Next
    INDEX
    Explanations

    enzyme-linked immunosorbent assay

    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
    æĪĸå¤ļæĪĸå°ij
    -0.08
     overloaded
    -0.07
     cha
    -0.07
    à¸Ńà¸ĩ
    -0.07
    LING
    -0.06
    eteor
    -0.06
    为äºĨ让
    -0.06
     desidera
    -0.06
    udit
    -0.06
    onga
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.09
    æĪĸèĢħ缴æİ¥
    0.08
    åı¯éĿł
    0.08
    ipay
    0.08
    มัà¹Īà¸Ļà¸Ħà¸ĩ
    0.07
     accurate
    0.07
    enabled
    0.07
    确认
    0.07
    abled
    0.07
    åı¯éĿłçļĦ
    0.07
    Activations Density 0.277%

    No Known Activations