© 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. 3985
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ('@/
    -0.23
     pute
    -0.21
    riz
    -0.20
    ¦¬
    -0.19
    .newaxis
    -0.19
     dresser
    -0.18
    .uri
    -0.18
    <stdlib
    -0.18
    izoph
    -0.18
    iterated
    -0.18
    POSITIVE LOGITS
    ();++
    0.26
    .mx
    0.23
    cej
    0.23
    ächst
    0.21
    âĦī
    0.20
     Psr
    0.20
    çĦ¶åIJİåĨį
    0.20
    ém
    0.19
    .angular
    0.19
     ÙĬÙĪس
    0.19
    Activations Density 0.059%

    No Known Activations