© 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. 54237
    Prev
    Next
    INDEX
    Explanations

    names like Higgins, McDowell

    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
     Cust
    -0.09
     bey
    -0.09
     Rig
    -0.09
    ả
    -0.09
     minut
    -0.09
     Canc
    -0.09
     Ord
    -0.09
    %^
    -0.09
     dedic
    -0.09
    orden
    -0.08
    POSITIVE LOGITS
    âĢij
    0.08
     jur
    0.08
     swept
    0.07
    Bur
    0.07
    âĢ
    0.07
     lobster
    0.07
    334
    0.07
     Bur
    0.07
    -ish
    0.07
     McCorm
    0.07
    Activations Density 0.006%

    No Known Activations