© 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. 3168
    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
    %;">
    -0.23
    ãĤ¢ãĥ¼
    -0.22
    atype
    -0.20
    vron
    -0.19
    imageName
    -0.19
    .mybatis
    -0.19
     },↵↵↵
    -0.19
    |{↵
    -0.18
    @Web
    -0.18
    .idea
    -0.18
    POSITIVE LOGITS
    rvine
    0.25
    gnore
    0.24
     Spicer
    0.21
    доб
    0.20
    á»ĭ
    0.20
     Hã
    0.20
    /callback
    0.19
     étape
    0.19
    scripción
    0.19
    âĸ¾
    0.19
    Activations Density 0.000%

    No Known Activations