© 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. 58955
    Prev
    Next
    INDEX
    Explanations

    apply method calls

    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
    Negative Logits
    oun
    -0.08
    ula
    -0.08
    ses
    -0.07
    ier
    -0.07
     intense
    -0.07
    ingly
    -0.07
    ings
    -0.07
    less
    -0.06
    ez
    -0.06
    uality
    -0.06
    POSITIVE LOGITS
    enso
    0.12
    fait
    0.11
    loff
    0.11
    chwitz
    0.11
    orld
    0.10
    okit
    0.10
    s
    0.10
    bject
    0.10
    leine
    0.10
     fw
    0.10
    Activations Density 0.003%

    No Known Activations