© 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. 57789
    Prev
    Next
    INDEX
    Explanations

    "I said" or "I mentioned"

    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
     Harvey
    -0.08
    ière
    -0.08
    olo
    -0.08
    campo
    -0.07
    lest
    -0.07
    steder
    -0.07
     Becker
    -0.07
     Minist
    -0.07
    und
    -0.07
     Olivier
    -0.07
    POSITIVE LOGITS
     Claim
    0.09
     sme
    0.09
    och
    0.09
     recently
    0.08
     Meth
    0.08
    ansa
    0.08
    ÑĥÑģ
    0.08
     Born
    0.08
     Wax
    0.08
    claim
    0.08
    Activations Density 0.006%

    No Known Activations