© 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. 6
    Prev
    Next
    INDEX
    Explanations

    by words like politicians, President

    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
     Contractors
    -0.10
     ambassador
    -0.10
    afort
    -0.09
     foreigners
    -0.09
     Contractor
    -0.09
     Ambassador
    -0.09
     traveller
    -0.08
     athlete
    -0.08
     gol
    -0.08
    affen
    -0.08
    POSITIVE LOGITS
     authorities
    0.14
     local
    0.11
     concerned
    0.10
    è£
    0.10
     senior
    0.10
     representatives
    0.10
    oki
    0.09
     responsible
    0.09
     cogn
    0.09
    inish
    0.09
    Activations Density 2.073%

    No Known Activations