© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    past participle verbs following auxiliary verbs

    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
     Bij
    -0.08
    eti
    -0.08
    998
    -0.07
    IDL
    -0.07
    aph
    -0.07
    avig
    -0.07
     resid
    -0.07
    kl
    -0.07
    638
    -0.07
     Basket
    -0.07
    POSITIVE LOGITS
    ngen
    0.09
    ...');↵
    0.09
    lation
    0.09
    ifiant
    0.09
    -gnu
    0.09
    uy
    0.09
    uye
    0.09
     maid
    0.08
     cons
    0.08
    onus
    0.08
    Activations Density 0.387%

    No Known Activations