© 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. 61392
    Prev
    Next
    INDEX
    Explanations

    itself

    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
    ocos
    -0.12
    oose
    -0.11
    shaw
    -0.11
    nock
    -0.10
    ibbon
    -0.10
    ",-
    -0.10
     Singleton
    -0.10
    ');↵↵↵↵
    -0.10
     sû
    -0.10
    OUS
    -0.10
    POSITIVE LOGITS
     itself
    0.09
     ourselves
    0.09
     themselves
    0.09
     fellow
    0.08
     herself
    0.07
    ADS
    0.07
     Himself
    0.07
    filtr
    0.07
    ernal
    0.07
    -fill
    0.06
    Activations Density 0.087%

    No Known Activations