© 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. 49530
    Prev
    Next
    INDEX
    Explanations

    alia congratulates

    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
    itter
    -0.07
    ys
    -0.07
    ilia
    -0.06
    æŨ
    -0.06
    å¸Ń
    -0.06
    æºĸ
    -0.06
    æĮĩ示精ç¥ŀ
    -0.06
     adipiscing
    -0.05
    å®ļæľŁ
    -0.05
    į
    -0.05
    POSITIVE LOGITS
    ewel
    0.09
    bacher
    0.08
    aná
    0.08
    eced
    0.08
    trer
    0.08
     Svg
    0.08
    odar
    0.08
    arca
    0.08
    uracion
    0.08
    ',[
    0.08
    Activations Density 0.004%

    No Known Activations