© 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. 61225
    Prev
    Next
    INDEX
    Explanations

    paths and commands

    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
    ãģĹãģĭ
    -0.11
    .Try
    -0.10
    nger
    -0.10
    ragments
    -0.10
    orton
    -0.10
    tti
    -0.09
    ifter
    -0.09
    oft
    -0.09
    estival
    -0.09
    ember
    -0.09
    POSITIVE LOGITS
     scrim
    0.08
    avs
    0.08
     miscellaneous
    0.08
     advoc
    0.07
     apl
    0.07
     Recover
    0.07
     [_
    0.07
    recover
    0.07
     algún
    0.07
     med
    0.07
    Activations Density 0.003%

    No Known Activations