© 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. 58908
    Prev
    Next
    INDEX
    Explanations

    let, suppose, consider

    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
    ughs
    -0.09
    elin
    -0.09
    iar
    -0.09
    87
    -0.09
    SDL
    -0.09
    _ang
    -0.08
     Bott
    -0.08
    àµįà´
    -0.08
    iene
    -0.08
    bons
    -0.08
    POSITIVE LOGITS
    kt
    0.09
     consider
    0.09
    оваÑĢ
    0.09
    erchant
    0.08
    hear
    0.08
    ike
    0.08
    dera
    0.08
    upo
    0.08
     Patron
    0.08
    gens
    0.08
    Activations Density 0.019%

    No Known Activations