© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3052
    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
    éĩįè¦ģåİŁåĽł
    -0.21
     CircularProgress
    -0.21
    æĸĿ
    -0.20
    æīĵå¾Ĺ
    -0.19
    æĦıè§ģåıįé¦Ī
    -0.19
    GORITH
    -0.18
    éĹ®è¯¢
    -0.18
    Ļ¶
    -0.18
     undefined
    -0.18
     atof
    -0.18
    POSITIVE LOGITS
    acerb
    0.25
    .ToShort
    0.23
    actices
    0.22
    ;!
    0.22
    ulings
    0.22
    estruction
    0.21
    .ParseException
    0.21
    resden
    0.21
    /INFO
    0.21
    箩
    0.21
    Activations Density 0.000%

    No Known Activations