© 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. 4000
    Prev
    Next
    INDEX
    Explanations

    Code structure

    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
    (/^\
    -0.21
    ç¨į
    -0.21
    '+↵
    -0.20
    \Abstract
    -0.20
    åĽŃ
    -0.19
    chine
    -0.19
     UnsupportedOperationException
    -0.19
    pest
    -0.19
    /
    -0.19
     I
    -0.19
    POSITIVE LOGITS
    polator
    0.27
    ;↵↵
    0.25
    OffsetTable
    0.25
    ?option
    0.24
     ÑģеÑĢÑĮезн
    0.23
    /slider
    0.22
    ccione
    0.22
    ;↵
    0.22
    åļĨ
    0.21
    nds
    0.21
    Activations Density 0.309%

    No Known Activations