© 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. 4055
    Prev
    Next
    INDEX
    Explanations

    technical detailed overview

    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
     addCriterion
    -0.21
    erglass
    -0.21
     équipé
    -0.21
    @ResponseBody
    -0.20
    @PostMapping
    -0.20
    	explicit
    -0.20
    olio
    -0.19
    æ²Ķ
    -0.19
    éparation
    -0.19
    ,},↵
    -0.19
    POSITIVE LOGITS
    åľ¨çº¿åĴ¨è¯¢
    0.20
    ;amp
    0.20
    cstdint
    0.19
     ë§Įìķ½
    0.19
    .FileReader
    0.18
    ç¼ĸ
    0.18
     ust
    0.18
    ,strlen
    0.18
    ?type
    0.18
    .epam
    0.18
    Activations Density 0.028%

    No Known Activations