© 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. 61993
    Prev
    Next
    INDEX
    Explanations

    model

    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
     hl
    -0.08
     Gus
    -0.08
    .Writer
    -0.08
     hilar
    -0.08
     Dahl
    -0.08
     investigators
    -0.07
     mash
    -0.07
     creatively
    -0.07
     Ps
    -0.07
    efe
    -0.07
    POSITIVE LOGITS
     Vanity
    0.11
    leo
    0.10
    /prom
    0.09
    lex
    0.09
     spokes
    0.09
    idl
    0.09
    ynchronize
    0.09
     Models
    0.09
     escort
    0.09
     Monsanto
    0.09
    Activations Density 0.049%

    No Known Activations