© 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. 451
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    pane
    -0.09
     Bray
    -0.08
    serter
    -0.08
     Resolver
    -0.08
    inel
    -0.08
    -helper
    -0.08
    agit
    -0.08
     flushing
    -0.08
     flush
    -0.08
     *,↵
    -0.08
    POSITIVE LOGITS
    eter
    0.20
    forth
    0.11
     rel
    0.11
    ETER
    0.10
    ehr
    0.09
    eteria
    0.09
    icos
    0.09
    .,
    0.09
     forth
    0.09
     sund
    0.09
    Activations Density 0.742%

    No Known Activations