© 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. 267
    Prev
    Next
    INDEX
    Explanations

    descriptive elements

    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
    ç¥Ľæĸij
    -0.24
     scaleX
    -0.23
    姹
    -0.22
    !important
    -0.21
    quiries
    -0.21
    çĤ¹åįĬ
    -0.21
    é¾ĥ
    -0.20
    ernaut
    -0.20
     =>'
    -0.20
    åİŁæĸĩåľ°åĿĢ
    -0.20
    POSITIVE LOGITS
     description
    0.31
     detailed
    0.27
     createSelector
    0.27
    /inet
    0.26
     diagram
    0.25
    :<?
    0.24
    ç®Ģ
    0.24
    详ç»ĨçļĦ
    0.24
     list
    0.23
    exemple
    0.23
    Activations Density 5.497%

    No Known Activations