© 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. 2235
    Prev
    Next
    INDEX
    Explanations

    said + noun

    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
    ign
    -0.08
    berg
    -0.08
    aram
    -0.08
     retali
    -0.07
    tra
    -0.07
    alue
    -0.07
     Borough
    -0.07
    ateg
    -0.07
     chaud
    -0.07
     Mou
    -0.07
    POSITIVE LOGITS
    kle
    0.11
     ~=
    0.09
    lest
    0.09
     kle
    0.08
     (=
    0.08
    EZ
    0.08
     ominous
    0.08
     #↵↵
    0.08
    edith
    0.08
     cree
    0.08
    Activations Density 0.047%

    No Known Activations