© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 549
    Prev
    Next
    INDEX
    Explanations

    state of political/geographic entities

    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
     rusty
    -0.11
     spit
    -0.11
    .Microsoft
    -0.10
    ticks
    -0.10
    lyn
    -0.10
    statt
    -0.10
    ETA
    -0.10
    ihu
    -0.09
    laus
    -0.09
    abe
    -0.09
    POSITIVE LOGITS
    wide
    0.20
    /local
    0.16
    hood
    0.13
    MENT
    0.13
    -sponsored
    0.13
    -wide
    0.12
    ful
    0.12
    MENTS
    0.11
    /state
    0.11
    -level
    0.11
    Activations Density 0.688%

    No Known Activations