© 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. 2435
    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
    forgettable
    -0.23
    utex
    -0.21
    OCUMENT
    -0.21
    aju
    -0.21
    itous
    -0.21
    âĬĶ
    -0.20
    ongoose
    -0.20
    omid
    -0.20
    entar
    -0.20
    'L
    -0.20
    POSITIVE LOGITS
    çĤĿ
    0.23
    æĢ§ä»·
    0.22
    IRTUAL
    0.21
    byterian
    0.21
    innacle
    0.21
    į°ìĿ´
    0.21
     springfox
    0.20
    深交
    0.20
     tats
    0.19
    åıĪ
    0.19
    Activations Density 0.002%

    No Known Activations