© 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. 2458
    Prev
    Next
    INDEX
    Explanations

    and followed by verb

    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
    oton
    -0.10
    cec
    -0.10
    uci
    -0.09
    illet
    -0.09
    ÑĮÑİ
    -0.09
     Pas
    -0.09
    enci
    -0.09
    &m
    -0.09
     Maver
    -0.09
    vip
    -0.09
    POSITIVE LOGITS
     become
    0.11
    Become
    0.09
    bec
    0.09
     becomes
    0.08
     emerge
    0.08
     ust
    0.08
     truly
    0.08
    oster
    0.08
    æĪIJ
    0.08
     Become
    0.08
    Activations Density 0.231%

    No Known Activations