© 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. 861
    Prev
    Next
    INDEX
    Explanations

    concessive clauses

    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
     moreover
    -0.10
     Either
    -0.08
     either
    -0.08
     furthermore
    -0.08
    Ä±ÅŁ
    -0.08
    ois
    -0.08
     instead
    -0.08
     thai
    -0.08
    asi
    -0.08
    epend
    -0.08
    POSITIVE LOGITS
     technically
    0.18
     nomin
    0.17
     ostensibly
    0.15
     theoretically
    0.15
     individually
    0.14
     initially
    0.13
     admittedly
    0.13
     seemingly
    0.12
     still
    0.12
     originally
    0.12
    Activations Density 0.632%

    No Known Activations