© 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. 4073
    Prev
    Next
    INDEX
    Explanations

    introducing new ideas or concepts

    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
     Latest
    -0.10
    aris
    -0.10
    eco
    -0.09
    bé
    -0.09
     Od
    -0.08
     exclus
    -0.08
    labs
    -0.08
     Eug
    -0.08
     occasionally
    -0.08
     wishes
    -0.08
    POSITIVE LOGITS
     innovations
    0.10
     idea
    0.10
     pioneering
    0.10
     paved
    0.09
     stabil
    0.09
     modern
    0.09
     concept
    0.09
     improvements
    0.09
    modern
    0.09
     pioneer
    0.08
    Activations Density 0.258%

    No Known Activations