© 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. 4735
    Prev
    Next
    INDEX
    Explanations

    four races

    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
    Not in Any Lists

    No Comments

    Negative Logits
     later
    -0.14
    later
    -0.12
     Grad
    -0.11
     Later
    -0.10
    Later
    -0.10
     afterward
    -0.10
     eventually
    -0.09
     Trav
    -0.09
     afterwards
    -0.09
     subsequently
    -0.09
    POSITIVE LOGITS
     wholes
    0.10
     rever
    0.09
    kon
    0.08
    ACHE
    0.08
     ort
    0.08
     hammer
    0.08
     peg
    0.08
    arian
    0.07
     leading
    0.07
    .new
    0.07
    Activations Density 0.062%

    No Known Activations