© 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. 54039
    Prev
    Next
    INDEX
    Explanations

    disclosure of invention

    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
    Not in Any Lists

    No Comments

    Negative Logits
    uze
    -0.11
    ci
    -0.10
     Dre
    -0.10
     accredited
    -0.09
    furt
    -0.09
    :\/\/
    -0.09
    FG
    -0.09
    ackers
    -0.09
     Bi
    -0.09
    unge
    -0.09
    POSITIVE LOGITS
    vd
    0.08
    -grey
    0.08
    .har
    0.08
    canf
    0.08
     teng
    0.07
    æk
    0.07
     cont
    0.07
     Butter
    0.07
    eds
    0.07
    wed
    0.07
    Activations Density 0.002%

    No Known Activations