© 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. 8081
    Prev
    Next
    INDEX
    Explanations

    names of places or things follow

    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
    fal
    -0.10
     Rotary
    -0.10
    --[[
    -0.09
    fce
    -0.09
     dipped
    -0.09
    achs
    -0.09
     rotary
    -0.09
     Epoch
    -0.09
    hani
    -0.09
    swer
    -0.09
    POSITIVE LOGITS
     distinct
    0.10
     nog
    0.08
     pink
    0.08
     saddle
    0.08
     dedicated
    0.08
     separate
    0.08
    ento
    0.07
    puties
    0.07
     exists
    0.07
     straightforward
    0.07
    Activations Density 0.557%

    No Known Activations