© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    column-count property

    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
    acl
    -0.10
    /Form
    -0.10
    errat
    -0.10
    zend
    -0.09
    urger
    -0.09
     dominated
    -0.09
    kov
    -0.09
    erne
    -0.09
    edio
    -0.09
    avig
    -0.09
    POSITIVE LOGITS
    ³³³
    0.12
    Âł
    0.11
    ³³³³³³³
    0.11
    ³³³³³³³³
    0.10
    ³³³³
    0.10
    Âł↵
    0.09
    ³³
    0.09
    lect
    0.09
     Emil
    0.09
    les
    0.09
    Activations Density 0.115%

    No Known Activations