© 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. 53840
    Prev
    Next
    INDEX
    Explanations

    java class names

    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
    anness
    -0.09
     Appet
    -0.08
     unders
    -0.08
    acman
    -0.08
     Crush
    -0.08
    Drop
    -0.08
     leng
    -0.08
    onne
    -0.08
    ampa
    -0.08
     dl
    -0.08
    POSITIVE LOGITS
    leta
    0.09
    ctor
    0.09
     Piper
    0.09
    JC
    0.08
    lec
    0.08
    STS
    0.08
    thic
    0.08
     Bron
    0.08
    Iso
    0.08
    ä
    0.08
    Activations Density 0.001%

    No Known Activations