© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 262
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
     crossorigin
    -0.23
    orgeous
    -0.21
    0
    -0.21
    èīı
    -0.20
     ðŁĺī↵↵
    -0.20
    <=$
    -0.20
     BindingFlags
    -0.20
    aeda
    -0.19
    EXTERN
    -0.19
    toPromise
    -0.19
    POSITIVE LOGITS
     çĶŁåij½åij¨æľŁ
    0.30
    è¹Ĥ
    0.27
    .PerformLayout
    0.25
     rekl
    0.23
    .Sockets
    0.22
    æijŃ
    0.21
     konk
    0.21
    åĺ¹
    0.21
    )&&(
    0.21
    .yy
    0.21
    Activations Density 5.812%

    No Known Activations