© 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. 353
    Prev
    Next
    INDEX
    Explanations

    corner/corner stone

    np_max-act-logits · gemini-2.5-flash-lite
    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
    ubbo
    -0.36
    readcr
    -0.34
    elsinki
    -0.33
     addCriterion
    -0.33
     sluts
    -0.32
    (Have
    -0.30
    ornment
    -0.30
    etroit
    -0.29
     bureaucr
    -0.28
    ICTURE
    -0.28
    POSITIVE LOGITS
    loggedin
    0.23
    ethoven
    0.21
     кожи
    0.21
    пÑĢом
    0.21
    åĦĨ
    0.20
    çħ
    0.20
    scrição
    0.19
    asset
    0.19
    	fflush
    0.19
    trieve
    0.19
    Activations Density 11.647%

    No Known Activations