© 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. 833
    Prev
    Next
    INDEX
    Explanations

    noun followed by modal verbs or forms of 'to be'

    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
     gotten
    -0.11
    irlines
    -0.11
     stemmed
    -0.11
     Pays
    -0.11
     lorsque
    -0.11
     arisen
    -0.10
    thinkable
    -0.10
     when
    -0.10
     withd
    -0.10
     withdrawn
    -0.10
    POSITIVE LOGITS
     can
    0.20
     is
    0.17
     could
    0.17
     may
    0.17
     might
    0.17
     will
    0.17
     would
    0.17
     was
    0.16
     must
    0.15
     cannot
    0.15
    Activations Density 4.598%

    No Known Activations