© 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. 18471
    Prev
    Next
    INDEX
    Explanations

    down and off states

    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
    -vous
    -0.13
    rippling
    -0.10
    ipse
    -0.10
    közi
    -0.09
    ViewById
    -0.09
    ornings
    -0.09
    ãģĺãĤģãģ¦
    -0.09
    wunsch
    -0.09
    UILD
    -0.08
    ×Ļ×Ŀ
    -0.08
    POSITIVE LOGITS
    à¹Ĩ
    0.10
    ward
    0.09
    manship
    0.09
    lit
    0.09
    ness
    0.09
     à¹Ĩ
    0.09
    side
    0.08
    m
    0.08
    -
    0.08
    âĢij
    0.08
    Activations Density 0.126%

    No Known Activations