© 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. 4740
    Prev
    Next
    INDEX
    Explanations

    be or become

    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
     can
    -0.13
     would
    -0.12
     will
    -0.12
     could
    -0.11
     shall
    -0.11
     may
    -0.10
    ’ll
    -0.10
    WND
    -0.10
     might
    -0.10
    can
    -0.10
    POSITIVE LOGITS
     be
    0.24
     бÑĭÑĤÑĮ
    0.20
     become
    0.17
     come
    0.15
    _be
    0.13
     être
    0.12
     være
    0.12
     appear
    0.12
     suffice
    0.12
    be
    0.12
    Activations Density 0.315%

    No Known Activations