© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1947
    Prev
    Next
    INDEX
    Explanations

    boundary or border

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interiors
    -0.10
    fulness
    -0.10
     inline
    -0.09
     tritur
    -0.09
    ê°Ħ
    -0.09
    wo
    -0.09
    ogan
    -0.09
    hum
    -0.09
    yon
    -0.09
    FromString
    -0.09
    POSITIVE LOGITS
     surrounding
    0.13
     layer
    0.13
    /interfaces
    0.12
     enclosing
    0.12
     layers
    0.11
     boundary
    0.11
    /interface
    0.11
     separating
    0.11
     boundaries
    0.11
     perimeter
    0.10
    Activations Density 1.582%

    No Known Activations