© 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. 299
    Prev
    Next
    INDEX
    Explanations

    authorised recognisable specialised organisations

    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
     neighborhood
    -0.26
     favorable
    -0.25
     favor
    -0.25
     harbor
    -0.24
     behaviors
    -0.24
     neighborhoods
    -0.24
     theater
    -0.23
     honored
    -0.23
     center
    -0.23
     behavior
    -0.23
    POSITIVE LOGITS
     whilst
    0.39
    Whilst
    0.38
     Whilst
    0.36
     recognised
    0.35
     organised
    0.31
     authorised
    0.31
     organisations
    0.31
     organisation
    0.31
     specialised
    0.31
     realised
    0.30
    Activations Density 7.321%

    No Known Activations