© 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. 1973
    Prev
    Next
    INDEX
    Explanations

    formal language

    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
     neighborhood
    -0.46
    neighbor
    -0.45
    Behavior
    -0.44
     neighborhoods
    -0.43
     neighbors
    -0.43
     behaviors
    -0.43
     neighbor
    -0.42
     neighboring
    -0.41
     favor
    -0.41
     favorite
    -0.40
    POSITIVE LOGITS
    Whilst
    0.60
     Whilst
    0.48
     whilst
    0.46
     ‘
    0.37
    ‘
    0.35
     enquiries
    0.32
     organisations
    0.31
    isation
    0.30
     envis
    0.30
    colour
    0.30
    Activations Density 15.166%

    No Known Activations