© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2965
    Prev
    Next
    INDEX
    Explanations

    say "start of technical text"

    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
    èIJ¤
    -0.21
     PureComponent
    -0.21
    æĬ¥ä»ĩ
    -0.20
    <SpriteRenderer
    -0.20
    è¯ĭ
    -0.20
     Anders
    -0.19
    éĵ¤
    -0.19
    imers
    -0.19
     Hamp
    -0.19
    rac
    -0.19
    POSITIVE LOGITS
     koje
    0.24
     INCIDENT
    0.23
     GANG
    0.22
    .elementAt
    0.21
     Decompiled
    0.20
    -scalable
    0.20
    	LEFT
    0.20
     enthus
    0.20
     PRODUCTS
    0.20
     Bros
    0.20
    Activations Density 0.001%

    No Known Activations