© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    border and neighbors

    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
     bott
    -0.10
     subordinate
    -0.09
     Bott
    -0.09
     globe
    -0.09
     bottleneck
    -0.08
    erea
    -0.08
     Glob
    -0.08
     everywhere
    -0.08
     places
    -0.08
    _mini
    -0.08
    POSITIVE LOGITS
     border
    0.19
     neighboring
    0.19
     adjacent
    0.19
     neighbors
    0.18
     neighbours
    0.18
     neighbor
    0.18
     neighbouring
    0.18
     adjoining
    0.17
     neighbour
    0.17
    border
    0.16
    Activations Density 0.384%

    No Known Activations