© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55082
    Prev
    Next
    INDEX
    Explanations

    technical processes and instrumentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    eti
    -0.09
     Smash
    -0.09
    foundland
    -0.08
     WCS
    -0.08
     recreated
    -0.08
    iais
    -0.08
     Patrol
    -0.08
     Premium
    -0.08
     bod
    -0.08
     smugg
    -0.08
    POSITIVE LOGITS
    ured
    0.10
     centuries
    0.10
     existing
    0.09
    stre
    0.09
     familiar
    0.09
    kel
    0.09
    chan
    0.09
     Century
    0.09
    inf
    0.08
     Millions
    0.08
    Activations Density 0.070%

    No Known Activations