© 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. 40885
    Prev
    Next
    INDEX
    Explanations

    tables and data structures

    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
    dirs
    -0.08
    opoulos
    -0.08
    boten
    -0.07
    oom
    -0.07
     nargin
    -0.07
    rage
    -0.07
    /Framework
    -0.07
    acey
    -0.07
    cept
    -0.07
     clearTimeout
    -0.07
    POSITIVE LOGITS
     data
    0.11
    æķ°æį®
    0.11
    çļĦæķ°æį®
    0.11
    æķ°æį®çļĦ
    0.11
     columns
    0.10
     rows
    0.10
     Columns
    0.10
     records
    0.10
    -data
    0.10
    data
    0.10
    Activations Density 0.878%

    No Known Activations