© 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. 8699
    Prev
    Next
    INDEX
    Explanations

    but WITHOUT

    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
    /tmp
    -0.11
    assa
    -0.11
    ?>↵↵↵
    -0.10
    mps
    -0.10
    undy
    -0.10
    UTE
    -0.10
    /Input
    -0.10
     Foley
    -0.09
    ilt
    -0.09
    .future
    -0.09
    POSITIVE LOGITS
     sponsors
    0.08
     Guaranteed
    0.07
     Cassandra
    0.07
     guaranteed
    0.07
    enco
    0.07
    .if
    0.06
    prob
    0.06
     Rolex
    0.06
     Sponsor
    0.06
     maint
    0.06
    Activations Density 0.035%

    No Known Activations