© 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. 55547
    Prev
    Next
    INDEX
    Explanations

    idea or concept

    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
     allied
    -0.10
    CCC
    -0.09
    ated
    -0.09
    Hands
    -0.09
     ranged
    -0.09
    uger
    -0.09
    ización
    -0.09
    kir
    -0.08
    coli
    -0.08
     stir
    -0.08
    POSITIVE LOGITS
     Cooke
    0.08
     converse
    0.08
    sid
    0.08
    rack
    0.08
     Mull
    0.07
     mere
    0.07
     OP
    0.07
     inability
    0.07
    raud
    0.07
    neys
    0.07
    Activations Density 0.045%

    No Known Activations