© 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. 8183
    Prev
    Next
    INDEX
    Explanations

    Montgomery Rice, Bryan Marion

    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
    tur
    -0.10
    LOGGER
    -0.09
    CAT
    -0.09
     honor
    -0.09
     IReadOnly
    -0.09
     Kob
    -0.09
    .extension
    -0.09
    enic
    -0.09
    ANNOT
    -0.08
    unya
    -0.08
    POSITIVE LOGITS
     McDon
    0.08
    Ñĥг
    0.07
    ctl
    0.07
    Thumb
    0.07
    efe
    0.06
    chk
    0.06
    nad
    0.06
     Intercept
    0.06
    Html
    0.06
    nge
    0.06
    Activations Density 1.151%

    No Known Activations