© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    code fragments and programming help

    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
     Rei
    -0.08
     Slim
    -0.08
     interrog
    -0.08
    /community
    -0.08
     tact
    -0.08
    verb
    -0.08
    GRES
    -0.07
     researching
    -0.07
     Chambers
    -0.07
     Tatto
    -0.07
    POSITIVE LOGITS
    apan
    0.10
    bach
    0.09
     rh
    0.09
    demo
    0.09
    rh
    0.09
    _D
    0.09
    aire
    0.09
    ám
    0.08
     folly
    0.08
    uge
    0.08
    Activations Density 0.810%

    No Known Activations