© 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. 252
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by future/modal 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
    ODO
    -0.09
     didnt
    -0.09
    olio
    -0.08
    arem
    -0.08
    .define
    -0.08
     homers
    -0.08
     meanwhile
    -0.07
     Juda
    -0.07
     gab
    -0.07
    ICA
    -0.07
    POSITIVE LOGITS
     chances
    0.18
     then
    0.15
     surely
    0.15
     automatically
    0.15
     alors
    0.15
     likely
    0.14
    then
    0.13
     will
    0.13
     immediately
    0.13
    Then
    0.12
    Activations Density 1.459%

    No Known Activations