© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3093
    Prev
    Next
    INDEX
    Explanations

    figure out

    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
     Bates
    -0.10
     agre
    -0.10
    moth
    -0.10
     Bounty
    -0.10
    ippets
    -0.09
    leta
    -0.09
    Proto
    -0.09
    ]:↵↵↵
    -0.09
    :",↵
    -0.09
     freelance
    -0.09
    POSITIVE LOGITS
     ties
    0.09
     tying
    0.09
     figuring
    0.08
     Tie
    0.08
     feels
    0.07
     neck
    0.07
     tied
    0.07
    om
    0.07
    alk
    0.07
    olio
    0.07
    Activations Density 0.937%

    No Known Activations