© 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. 61247
    Prev
    Next
    INDEX
    Explanations

    Source definitions

    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
     continuing
    -0.07
    asar
    -0.07
    ...
    -0.06
    olly
    -0.06
    esh
    -0.06
    .rf
    -0.06
     colspan
    -0.06
     awaiting
    -0.06
    ...↵
    -0.06
    ISS
    -0.06
    POSITIVE LOGITS
     mornings
    0.10
    vana
    0.10
    ado
    0.10
     ratt
    0.10
    wel
    0.10
    ):-
    0.10
    Bag
    0.10
    ADOS
    0.10
    gettext
    0.10
     setHidden
    0.10
    Activations Density 0.012%

    No Known Activations