© 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. 8177
    Prev
    Next
    INDEX
    Explanations

    Internet Protocol, OLED, opioid, ligand

    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
    usch
    -0.08
     Ready
    -0.08
    oken
    -0.07
    uil
    -0.07
     prepares
    -0.07
     expectation
    -0.07
    bor
    -0.07
    Tumblr
    -0.07
     OLD
    -0.06
     Gil
    -0.06
    POSITIVE LOGITS
     modified
    0.13
     normally
    0.13
     Enhancement
    0.11
    (existing
    0.11
     otherwise
    0.11
     Normally
    0.11
    -like
    0.11
     existing
    0.11
    existing
    0.11
     already
    0.11
    Activations Density 0.937%

    No Known Activations