© 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. 58252
    Prev
    Next
    INDEX
    Explanations

    of two plates

    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
     shovel
    -0.08
     based
    -0.08
    âĢİ
    -0.08
     comparable
    -0.08
     comparative
    -0.08
    aina
    -0.08
     generado
    -0.08
    /item
    -0.08
     realistic
    -0.08
     Dak
    -0.07
    POSITIVE LOGITS
     roughly
    0.10
     âī
    0.10
    uya
    0.10
     prepar
    0.10
     Alto
    0.10
    ÙĪد
    0.10
     approximately
    0.10
    ulan
    0.10
    rides
    0.09
    654
    0.09
    Activations Density 0.050%

    No Known Activations