© 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. 2225
    Prev
    Next
    INDEX
    Explanations

    dates and structure

    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
    èĭ¡
    -0.23
    ');?>"
    -0.23
    []=$
    -0.22
    ,cp
    -0.22
    RuntimeObject
    -0.21
    æ°²
    -0.20
    BUFF
    -0.20
    .namespace
    -0.20
    æĺ¶
    -0.20
     .'</
    -0.19
    POSITIVE LOGITS
    æĭ£
    0.22
    FormsModule
    0.20
    æ±Ĥå©ļ
    0.20
     autoFocus
    0.19
    æľīçĶ¨
    0.19
    .LogWarning
    0.19
    åĵĪåĵĪåĵĪåĵĪ
    0.19
    åŁĤ
    0.19
     Mourinho
    0.19
    .gradient
    0.19
    Activations Density 0.008%

    No Known Activations