© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    levels and degrees

    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
    =$('#
    -0.22
    uele
    -0.21
    .Microsoft
    -0.21
    _nsec
    -0.20
    _)č↵
    -0.20
    æ±Ĩ
    -0.20
    .LoggerFactory
    -0.19
    ');?>↵
    -0.19
     homosex
    -0.19
    _KeyPress
    -0.19
    POSITIVE LOGITS
     beÄŁen
    0.28
    æ··åIJĪ
    0.25
    "default
    0.24
    :;↵
    0.24
     withd
    0.23
    翾
    0.23
    mixed
    0.23
    æĹłæīĢè°ĵ
    0.23
     decidedly
    0.23
     non
    0.23
    Activations Density 3.086%

    No Known Activations