© 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. 58804
    Prev
    Next
    INDEX
    Explanations

    spot + following word

    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
    abouts
    -0.11
    zem
    -0.11
    ettings
    -0.11
    ereg
    -0.11
    anse
    -0.11
    hift
    -0.11
    ænd
    -0.10
    or
    -0.10
    osate
    -0.10
    hin
    -0.10
    POSITIVE LOGITS
    ter
    0.18
    ting
    0.14
    lights
    0.14
    light
    0.12
    lands
    0.10
    ly
    0.10
    land
    0.09
    ron
    0.09
    ted
    0.09
    tery
    0.09
    Activations Density 0.009%

    No Known Activations