© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61388
    Prev
    Next
    INDEX
    Explanations

    specialised, organised, emphasised

    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
    Negative Logits
     neighboring
    -0.14
     favorable
    -0.14
     signaling
    -0.12
     neighbors
    -0.12
     neighbor
    -0.12
     favored
    -0.12
     favor
    -0.12
     maneuvers
    -0.12
     favors
    -0.12
    -0.12
    POSITIVE LOGITS
     organisation
    0.13
     organis
    0.13
     specialised
    0.12
     organised
    0.12
     organisations
    0.11
     emphas
    0.10
    organisation
    0.10
    rack
    0.10
     personalised
    0.10
    ï¸
    0.10
    Activations Density 0.067%

    No Known Activations