© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 842
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    Âł
    -0.26
     (
    -0.25
    requete
    -0.23
    (
    -0.22
    çIJ¨
    -0.22
    **
    -0.21
     [
    -0.21
    åĸĨ
    -0.21
    etAddress
    -0.20
    .↵↵
    -0.20
    POSITIVE LOGITS
    .scalablytyped
    0.27
    YG
    0.25
    é¾ĥ
    0.25
    ==========↵
    0.24
    âĦħ
    0.23
    :<?
    0.23
    ********************************************************************************
    0.23
     (){
    0.22
    GBT
    0.22
     INTERRUPTION
    0.22
    Activations Density 1.198%

    No Known Activations