© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61350
    Prev
    Next
    INDEX
    Explanations

    conjunctions and adverbs

    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
    Negative Logits
     mater
    -0.09
    rub
    -0.09
     bel
    -0.08
     Grinder
    -0.08
    ollo
    -0.08
    FX
    -0.08
    bart
    -0.08
    !:
    -0.08
    ients
    -0.08
     BG
    -0.08
    POSITIVE LOGITS
     firstly
    0.10
    anner
    0.09
     indeed
    0.08
     perch
    0.08
     atleast
    0.08
     if
    0.08
    wel
    0.08
     humanities
    0.08
    556
    0.08
    [âĢ¦]
    0.08
    Activations Density 0.102%

    No Known Activations