© 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. 61974
    Prev
    Next
    INDEX
    Explanations

    quote starts

    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
    erre
    -0.10
    pez
    -0.10
    iete
    -0.10
    ails
    -0.09
     rak
    -0.09
    ards
    -0.09
    church
    -0.09
    eka
    -0.09
    ond
    -0.09
     dew
    -0.09
    POSITIVE LOGITS
     “
    0.10
     “[
    0.10
     vibe
    0.08
    openh
    0.07
     ``
    0.07
     ".
    0.07
     "
    0.07
    eing
    0.07
     cleaner
    0.07
     «
    0.07
    Activations Density 0.029%

    No Known Activations