© 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. 560
    Prev
    Next
    INDEX
    Explanations

    introduce definitions

    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
     Jackets
    -0.26
     Erectile
    -0.23
    <decltype
    -0.22
     compareTo
    -0.21
     ()=>{↵
    -0.21
     enthus
    -0.21
     keyCode
    -0.20
     appré
    -0.20
     Bundy
    -0.20
     @$_
    -0.20
    POSITIVE LOGITS
     let
    0.30
    å®ļä¹ī
    0.29
     define
    0.28
    约å®ļ
    0.28
    æĪij们å°Ĩ
    0.28
     Let
    0.26
     now
    0.25
    设
    0.25
     convention
    0.25
     definitions
    0.24
    Activations Density 0.777%

    No Known Activations