© 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. 1118
    Prev
    Next
    INDEX
    Explanations

    happenings and meaning

    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
    iá»ĩn
    -0.23
    /rs
    -0.22
    :'',
    -0.21
    ä¸įåı¯æĪĸ缺
    -0.21
     ValueEventListener
    -0.20
    oproject
    -0.20
    GetSize
    -0.20
    åĸı
    -0.19
    avorites
    -0.19
    åIJĴ
    -0.19
    POSITIVE LOGITS
     happened
    0.29
     happens
    0.27
     means
    0.27
     happening
    0.27
     why
    0.27
     happen
    0.26
    æĦıåij³çĿĢ
    0.26
    为ä»Ģä¹Ī
    0.25
    æĺ¯åĽłä¸º
    0.25
     true
    0.24
    Activations Density 1.425%

    No Known Activations