© 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. 57633
    Prev
    Next
    INDEX
    Explanations

    how it happened

    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
    ughter
    -0.11
     paired
    -0.10
     sog
    -0.09
     abbrev
    -0.09
     pair
    -0.09
    esch
    -0.08
     declar
    -0.08
    435
    -0.08
    orton
    -0.08
    inst
    -0.08
    POSITIVE LOGITS
    Detailed
    0.12
     detailed
    0.11
     Procedure
    0.11
     Detailed
    0.10
     Details
    0.10
     procedure
    0.10
     details
    0.10
    Steps
    0.10
    ajas
    0.09
     step
    0.09
    Activations Density 0.155%

    No Known Activations