© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    scientific paper results

    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
     usually
    -0.12
     Usually
    -0.10
     nowadays
    -0.09
     famously
    -0.09
     or
    -0.09
    —or
    -0.09
     Typically
    -0.09
     any
    -0.09
     sometime
    -0.09
     (=
    -0.08
    POSITIVE LOGITS
     PMID
    0.14
     novel
    0.14
     RESULTS
    0.14
    LLU
    0.13
     ..."↵
    0.13
    .Key
    0.13
     unprecedented
    0.12
     unexpectedly
    0.12
    Results
    0.12
     Results
    0.11
    Activations Density 5.915%

    No Known Activations