© 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. 1406
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĿ
    -0.22
    .createTextNode
    -0.19
    ationToken
    -0.19
    ãģĨãģĵãģ¨
    -0.19
    ysters
    -0.19
    agoon
    -0.19
    æ¡Ģ
    -0.19
    åĨĪ
    -0.18
    geries
    -0.18
    oldt
    -0.18
    POSITIVE LOGITS
     ?>/
    0.23
    åĵĪåĵĪåĵĪåĵĪ
    0.22
    éĴ¡
    0.22
     (!((
    0.21
    ï½ŀ↵↵
    0.20
    <=$
    0.20
    SX
    0.20
    /Instruction
    0.20
     FindObjectOfType
    0.20
    __;
    0.19
    Activations Density 0.000%

    No Known Activations