© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    acronyms, citations, stories, traffic, challenges, effects, wrinkles, recipes

    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
    ",[
    -0.11
    "."
    -0.11
    /vendors
    -0.10
    —including
    -0.10
     grues
    -0.10
     pelos
    -0.10
    :".
    -0.10
    —"
    -0.10
    .",
    -0.10
     busty
    -0.10
    POSITIVE LOGITS
     anyway
    0.14
     etc
    0.13
     right
    0.13
     anyways
    0.12
     here
    0.12
     you
    0.11
     really
    0.11
     like
    0.11
     I
    0.11
     anyhow
    0.10
    Activations Density 4.194%

    No Known Activations