© 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. 61332
    Prev
    Next
    INDEX
    Explanations

    code keywords or declarations

    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
    æ¯
    -0.09
     volta
    -0.09
    esi
    -0.09
    egasus
    -0.09
    /Area
    -0.09
    otti
    -0.09
    rego
    -0.09
    SetValue
    -0.09
    Rejected
    -0.09
    apolis
    -0.08
    POSITIVE LOGITS
     otherwise
    0.09
    æĺ¯åIJ¦
    0.09
     Otherwise
    0.08
     pur
    0.08
     tran
    0.08
     Noir
    0.07
    ionic
    0.07
     Jas
    0.07
     Hugo
    0.07
    æ°
    0.07
    Activations Density 0.027%

    No Known Activations