© 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. 624
    Prev
    Next
    INDEX
    Explanations

    time of day

    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
    ómo
    -0.26
     repmat
    -0.23
     numel
    -0.21
     uranus
    -0.21
    æĭĥ
    -0.20
    ={()=>
    -0.20
    Ợ
    -0.19
    ãģĨãģĵãģ¨
    -0.19
    è¿Ļ两天
    -0.19
    .modelo
    -0.19
    POSITIVE LOGITS
     noon
    0.29
    am
    0.26
    oufl
    0.26
     midnight
    0.24
    pmat
    0.23
    åĩłçĤ¹
    0.23
    serter
    0.22
    ropri
    0.21
    AM
    0.21
    çľĭçĤ¹
    0.21
    Activations Density 0.429%

    No Known Activations