© 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. 53800
    Prev
    Next
    INDEX
    Explanations

    progress, direction, attention, expected

    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
     Rosenberg
    -0.08
    uri
    -0.07
    erule
    -0.07
     thumb
    -0.07
     tong
    -0.07
     summed
    -0.07
    alte
    -0.07
    ragen
    -0.07
     totalement
    -0.07
    umni
    -0.06
    POSITIVE LOGITS
     Mint
    0.11
    .Te
    0.10
     lineno
    0.10
    cee
    0.10
    icy
    0.10
    coop
    0.10
     Hof
    0.09
    tex
    0.09
     smack
    0.09
    OfYear
    0.09
    Activations Density 0.106%

    No Known Activations