© 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. 16417
    Prev
    Next
    INDEX
    Explanations

    film-, -maker, state

    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
    orada
    -0.08
    anner
    -0.07
    een
    -0.07
    haust
    -0.07
    xon
    -0.07
     heck
    -0.07
    enuity
    -0.07
    nok
    -0.07
    ately
    -0.07
    exo
    -0.07
    POSITIVE LOGITS
    linge
    0.07
    ÑĥкÑĢа
    0.06
     Filho
    0.06
    ä¸įèī¯å½±åĵį
    0.06
    PEC
    0.06
    ×Ļ×Ŀ
    0.06
     kÃŃn
    0.06
    apa
    0.06
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.06
    зма
    0.06
    Activations Density 0.257%

    No Known Activations