© 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. 2052
    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
    ]int
    -0.23
    ]bool
    -0.23
     ×Ķ×ķ×ĵ
    -0.23
    meye
    -0.22
    mö
    -0.22
     manh
    -0.21
    sthrough
    -0.21
    rippling
    -0.20
    enheim
    -0.20
     hust
    -0.20
    POSITIVE LOGITS
     )}↵↵
    0.21
    åĿĬ
    0.20
    ore
    0.20
    æŁ¥çľĭ详æĥħ
    0.20
    ResultsController
    0.19
    ormap
    0.18
     Alleg
    0.18
     rep
    0.18
    Enumerator
    0.18
    boro
    0.17
    Activations Density 0.000%

    No Known Activations