© 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. 2986
    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
    椿
    -0.22
    crate
    -0.21
    [$_
    -0.21
    entifier
    -0.21
    ä¸Ńåħ³
    -0.20
    åĻ«
    -0.20
    UrlParser
    -0.20
    :["
    -0.19
    alte
    -0.19
    çĩ¹
    -0.19
    POSITIVE LOGITS
     winger
    0.23
    Wunused
    0.21
    èģĶç½ij
    0.19
     Justi
    0.19
    asics
    0.19
    noc
    0.18
    ish
    0.18
    chet
    0.18
    æĬĬæĮģ
    0.18
    æĬĢå·§
    0.18
    Activations Density 0.000%

    No Known Activations