© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4532
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     Kirk
    -0.09
    .case
    -0.08
    Photos
    -0.08
     photos
    -0.08
     Stuart
    -0.08
     Orion
    -0.08
    ikon
    -0.08
    duck
    -0.08
     Photos
    -0.08
     Sussex
    -0.08
    POSITIVE LOGITS
    bolt
    0.11
    fall
    0.11
    arya
    0.09
    jam
    0.09
    ÑĮ
    0.08
    /people
    0.08
     bolt
    0.08
    gre
    0.08
    -zA
    0.08
    apter
    0.08
    Activations Density 0.682%

    No Known Activations