© 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. 26134
    Prev
    Next
    INDEX
    Explanations

    empty list or string

    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
    iglio
    -0.10
    HING
    -0.09
    ered
    -0.09
    erate
    -0.09
    erma
    -0.08
    erlo
    -0.08
    à¸Ļà¹Į
    -0.08
    ane
    -0.08
    ÏĦÎŃ
    -0.08
    ç½Ĺæĭī
    -0.08
    POSITIVE LOGITS
    人
    0.08
    iseau
    0.08
    ish
    0.06
    -même
    0.06
    "
    0.06
    ollections
    0.06
    ublish
    0.06
    &
    0.06
    ements
    0.06
    rensa
    0.05
    Activations Density 0.074%

    No Known Activations