© 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. 61773
    Prev
    Next
    INDEX
    Explanations

    .io exceptions, serializable, files

    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
     Pres
    -0.08
     Tent
    -0.07
    fully
    -0.07
     Conserv
    -0.07
    ake
    -0.07
    ات
    -0.06
    lop
    -0.06
    rupt
    -0.06
    Pres
    -0.06
     TECH
    -0.06
    POSITIVE LOGITS
    .IOException
    0.15
    .Serializable
    0.13
    ieres
    0.11
    Locations
    0.10
    .EOF
    0.10
     Licht
    0.10
     apk
    0.10
     misc
    0.10
    .Close
    0.10
    .File
    0.10
    Activations Density 0.001%

    No Known Activations