© 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. 31051
    Prev
    Next
    INDEX
    Explanations

    place names and names

    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
    1
    -0.08
    3
    -0.07
    -0.07
    0
    -0.07
     "
    -0.06
    2
    -0.06
    ered
    -0.06
    iliz
    -0.06
    5
    -0.06
    :
    -0.06
    POSITIVE LOGITS
    Ñģполни
    0.10
     contempora
    0.10
    дÑĮми
    0.10
    Ñģпали
    0.10
    лÑĩа
    0.09
    éĽ³
    0.09
    endela
    0.09
    моби
    0.09
    uccio
    0.09
    urier
    0.09
    Activations Density 0.320%

    No Known Activations