© 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. 2389
    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
    NSMutableDictionary
    -0.21
     sacrific
    -0.21
     veter
    -0.21
     algu
    -0.20
     sluts
    -0.20
    yn
    -0.19
    涧
    -0.19
    çªĹ
    -0.18
    ÙģعاÙĦÙĬ
    -0.18
    éĨĴäºĨ
    -0.18
    POSITIVE LOGITS
    quirrel
    0.23
    öffentlich
    0.23
    kaza
    0.23
    <Props
    0.23
    |array
    0.22
    .LogWarning
    0.22
     UIG
    0.21
    vla
    0.21
    ]("
    0.20
    ysz
    0.20
    Activations Density 0.001%

    No Known Activations