© 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. 58831
    Prev
    Next
    INDEX
    Explanations

    later became, later premier, later ex-boyfriend

    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
    ivel
    -0.10
     owe
    -0.09
    circ
    -0.09
    onis
    -0.09
    actly
    -0.09
    ÑĢам
    -0.09
    udence
    -0.09
    atten
    -0.09
     guilt
    -0.09
    vé
    -0.09
    POSITIVE LOGITS
     ditch
    0.08
     Peaks
    0.08
    eil
    0.07
    st
    0.07
     omn
    0.07
     ter
    0.07
     sl
    0.07
     Creatures
    0.07
    agi
    0.07
     Cork
    0.07
    Activations Density 0.010%

    No Known Activations