© 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. 61536
    Prev
    Next
    INDEX
    Explanations

    references numbering

    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
    àµį
    -0.10
     tapping
    -0.07
    ponder
    -0.07
    oldt
    -0.07
    ogue
    -0.06
    aber
    -0.06
     mont
    -0.06
    ulers
    -0.06
     wrink
    -0.06
     thro
    -0.06
    POSITIVE LOGITS
    ään
    0.12
    Trou
    0.10
    Absolute
    0.10
    <a
    0.10
    ONSE
    0.10
    elas
    0.10
     caratter
    0.10
    ž
    0.10
    Dam
    0.10
    .Word
    0.10
    Activations Density 0.001%

    No Known Activations