© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4280
    Prev
    Next
    INDEX
    Explanations

    Everything

    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
    Negative Logits
     ÑĥÑĩиÑĤÑĭва
    -0.24
    ITTLE
    -0.24
     sigu
    -0.24
    !=(
    -0.23
    ︱
    -0.22
    âĦī
    -0.22
    åįĥæĸ¹
    -0.21
     Dich
    -0.21
    ATAB
    -0.21
    "<?
    -0.21
    POSITIVE LOGITS
    theless
    0.23
    è¨İ
    0.21
     photoshop
    0.21
    è´£
    0.20
    verages
    0.20
    -know
    0.19
    soever
    0.19
    usterity
    0.19
    woke
    0.19
     stun
    0.19
    Activations Density 0.114%

    No Known Activations