© 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. 2189
    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
    eta
    -0.20
    æľĢå¿«çļĦ
    -0.20
    ory
    -0.19
    çĦĹ
    -0.18
    ope
    -0.18
    èIJĮ
    -0.18
     batteries
    -0.18
    Ùĩ
    -0.18
     sat
    -0.18
    age
    -0.18
    POSITIVE LOGITS
    ksam
    0.25
    %X
    0.25
    gunakan
    0.24
    -Cs
    0.23
    remium
    0.22
    lier
    0.22
    ething
    0.22
    armacy
    0.22
    nicos
    0.22
    .dtd
    0.22
    Activations Density 0.000%

    No Known Activations