© 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. 61666
    Prev
    Next
    INDEX
    Explanations

    numbers following publication IDs or data formats

    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
     orders
    -0.09
    Orders
    -0.09
    .Today
    -0.08
    -runtime
    -0.08
    alfa
    -0.08
    ypes
    -0.08
     Routine
    -0.08
    âĢ¦it
    -0.08
    ASY
    -0.08
    èĪ
    -0.08
    POSITIVE LOGITS
    .bi
    0.10
    emm
    0.09
     afar
    0.09
    vol
    0.08
    thro
    0.08
     ourselves
    0.08
    ello
    0.08
    lm
    0.08
    iac
    0.08
    Loc
    0.08
    Activations Density 0.028%

    No Known Activations