© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2765
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
    acons
    -0.21
    itorio
    -0.20
    .moveToNext
    -0.20
    ä¸ĭä¸Ģç¯ĩ
    -0.19
    piler
    -0.19
    ThanOr
    -0.19
     Snape
    -0.18
    æ°´åŁŁ
    -0.18
    å±Ĥåĩºä¸į
    -0.18
    //"
    -0.18
    POSITIVE LOGITS
    çĻ¾å¼º
    0.20
     ._
    0.19
    ane
    0.19
    å¸ĥç½®
    0.19
     Miller
    0.19
     UITextView
    0.19
    Carthy
    0.18
    åĪ«äººçļĦ
    0.18
     ="";↵
    0.18
    unda
    0.18
    Activations Density 0.005%

    No Known Activations