© 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. 61743
    Prev
    Next
    INDEX
    Explanations

    `_J` followed by `J`, `^` followed by `*`, `/H` followed by `OU`/`ac`

    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
    aya
    -0.08
    reo
    -0.07
    org
    -0.07
    ë
    -0.07
    ass
    -0.07
    iah
    -0.07
    relude
    -0.07
    ci
    -0.07
     Pasta
    -0.06
    isable
    -0.06
    POSITIVE LOGITS
    edi
    0.10
    .firstname
    0.09
    rage
    0.09
    baz
    0.09
     PropertyInfo
    0.09
    ldr
    0.09
     ATS
    0.09
    okit
    0.09
    893
    0.09
    inters
    0.09
    Activations Density 0.010%

    No Known Activations