© 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. 30754
    Prev
    Next
    INDEX
    Explanations

    file extensions and code elements

    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
    DataGridViewTextBoxColumn
    -0.09
    ç¯Ŀ
    -0.08
    纳士
    -0.07
    -0.07
    è¿Ļ个æķ°åŃĹ
    -0.07
    combo
    -0.07
    orners
    -0.07
     plazas
    -0.06
    ToolStripMenuItem
    -0.06
     ÙģرÙĪ
    -0.06
    POSITIVE LOGITS
    /Area
    0.09
    /List
    0.08
    idae
    0.08
    V
    0.08
    /Login
    0.08
    /N
    0.08
    /System
    0.08
    T
    0.08
    -State
    0.08
    TM
    0.07
    Activations Density 2.414%

    No Known Activations