© 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. 58939
    Prev
    Next
    INDEX
    Explanations

    filed pursuant to

    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
    ype
    -0.11
    ungeon
    -0.11
    esen
    -0.10
    urga
    -0.10
    -indent
    -0.10
    oad
    -0.09
    (Mouse
    -0.09
    (er
    -0.09
    rott
    -0.09
     iota
    -0.09
    POSITIVE LOGITS
    yst
    0.08
     disappoint
    0.08
    ko
    0.07
     accordingly
    0.07
    NCY
    0.07
     genu
    0.07
    mc
    0.06
    isch
    0.06
    .m
    0.06
     somebody
    0.06
    Activations Density 0.003%

    No Known Activations