© 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. 57514
    Prev
    Next
    INDEX
    Explanations

    plug-in / plugging

    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
    ering
    -0.12
     Cir
    -0.09
    ening
    -0.08
    ful
    -0.08
    atch
    -0.08
    .IC
    -0.08
    ancy
    -0.07
    orie
    -0.07
    aat
    -0.07
    erin
    -0.07
    POSITIVE LOGITS
    rub
    0.11
    ger
    0.11
    isky
    0.10
    ORN
    0.10
     reck
    0.10
     rake
    0.10
    sel
    0.10
    ugged
    0.09
    Rub
    0.09
    uvre
    0.09
    Activations Density 0.006%

    No Known Activations