© 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. 1549
    Prev
    Next
    INDEX
    Explanations

    names followed by quotes or actions

    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
     eaten
    -0.13
     conforms
    -0.12
     thrown
    -0.11
     screamed
    -0.11
     cheered
    -0.11
     revolves
    -0.11
     gotten
    -0.11
     progresses
    -0.10
     ought
    -0.10
     inspires
    -0.10
    POSITIVE LOGITS
    —who
    0.11
     then
    0.10
     also
    0.09
     gam
    0.08
    imd
    0.08
     blunt
    0.08
     facet
    0.08
     credits
    0.08
     joking
    0.08
     first
    0.08
    Activations Density 1.114%

    No Known Activations