© 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. 15574
    Prev
    Next
    INDEX
    Explanations

    someone followed by is

    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
    anos
    -0.08
    ary
    -0.07
    zcz
    -0.07
    اة
    -0.07
    lands
    -0.06
    NEL
    -0.06
    ä¸Ģ个ç®ĢåįķçļĦ
    -0.06
    à¸Ĺัà¹īà¸ĩหลาย
    -0.06
    anak
    -0.06
     escape
    -0.06
    POSITIVE LOGITS
    _else
    0.11
     else
    0.10
    thing
    0.10
    æĪĸå¤ļ个
    0.10
    else
    0.09
    eting
    0.09
    æĪĸå¤ļ
    0.09
    Else
    0.08
     anderem
    0.08
    akin
    0.08
    Activations Density 0.078%

    No Known Activations