© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1572
    Prev
    Next
    INDEX
    Explanations

    list items or phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuff
    -0.38
     Stuff
    -0.28
     functionality
    -0.27
    stuff
    -0.27
    _stuff
    -0.26
     advice
    -0.24
    ä¸Ģ人
    -0.23
     One
    -0.23
     Advice
    -0.23
    one
    -0.23
    POSITIVE LOGITS
    ".↵↵↵↵
    0.35
    IGHL
    0.35
    byss
    0.33
    ksam
    0.29
    :".$
    0.29
    ldre
    0.28
    actionDate
    0.28
    odyn
    0.28
    indsight
    0.27
    linky
    0.27
    Activations Density 1.185%

    No Known Activations