© 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. 53835
    Prev
    Next
    INDEX
    Explanations

    tree view

    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
    sr
    -0.10
     crus
    -0.09
     yapı
    -0.09
    ivy
    -0.08
    irse
    -0.08
     regular
    -0.08
    ych
    -0.08
    ioni
    -0.08
    ÑĢав
    -0.08
    /body
    -0.08
    POSITIVE LOGITS
    ango
    0.09
     ens
    0.08
     renov
    0.08
    ete
    0.08
    atk
    0.08
    lé
    0.07
     verm
    0.07
     Pres
    0.07
    æľŁ
    0.07
     Hans
    0.07
    Activations Density 0.001%

    No Known Activations