© 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. 58655
    Prev
    Next
    INDEX
    Explanations

    . R.R.M. or Fed. L. Rep

    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
     (!((
    -0.10
    lify
    -0.10
    AMA
    -0.10
    tener
    -0.09
    arget
    -0.09
    eselect
    -0.09
    lland
    -0.09
    ICAL
    -0.09
    ieten
    -0.09
    iken
    -0.09
    POSITIVE LOGITS
    are
    0.08
    chia
    0.08
    æk
    0.07
    æģ¯
    0.07
    irut
    0.07
     ali
    0.07
     Rem
    0.07
    or
    0.07
    oram
    0.07
    0.07
    Activations Density 0.001%

    No Known Activations