© 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. 3570
    Prev
    Next
    INDEX
    Explanations

    simply or easily done

    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
    locked
    -0.10
    scr
    -0.10
     shops
    -0.10
    odash
    -0.10
     scramble
    -0.10
     Shop
    -0.09
     shop
    -0.09
    grily
    -0.09
     permanently
    -0.09
    manual
    -0.09
    POSITIVE LOGITS
     simply
    0.15
     simple
    0.13
     Simply
    0.12
    Simply
    0.12
     Simple
    0.11
     effortless
    0.11
     mere
    0.11
     easy
    0.10
     merely
    0.10
    Simple
    0.10
    Activations Density 0.323%

    No Known Activations