© 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. 61776
    Prev
    Next
    INDEX
    Explanations

    energetically expensive and costly

    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
    ug
    -0.11
     Rodney
    -0.11
     Sever
    -0.10
    dma
    -0.10
     foreigners
    -0.10
    iod
    -0.10
    viz
    -0.09
     cuffs
    -0.09
    urb
    -0.09
    _SQL
    -0.09
    POSITIVE LOGITS
     guts
    0.07
     indiscrim
    0.07
     Punch
    0.07
     paired
    0.07
    ateful
    0.07
     selectively
    0.07
     autoload
    0.06
     warming
    0.06
     careless
    0.06
     spot
    0.06
    Activations Density 0.067%

    No Known Activations