© 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. 58704
    Prev
    Next
    INDEX
    Explanations

    `equal` checks

    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
    à©
    -0.10
    elow
    -0.10
    acci
    -0.09
     Hector
    -0.09
    py
    -0.09
    drive
    -0.09
    iona
    -0.08
     strategist
    -0.08
    xo
    -0.08
     decency
    -0.08
    POSITIVE LOGITS
    swith
    0.11
     nau
    0.09
    ods
    0.08
    yal
    0.08
    odb
    0.08
    overs
    0.08
    .ads
    0.08
    ongo
    0.08
    .her
    0.08
     Loren
    0.07
    Activations Density 0.001%

    No Known Activations