© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
     opc
    -0.10
    idth
    -0.10
    rib
    -0.10
    º«
    -0.10
    vit
    -0.09
    arest
    -0.09
     gab
    -0.09
    byss
    -0.09
     Lastly
    -0.09
    ETA
    -0.09
    POSITIVE LOGITS
     therefore
    0.17
     Therefore
    0.15
    Therefore
    0.13
     Yet
    0.12
     yet
    0.12
    Yet
    0.10
     so
    0.09
     Accordingly
    0.09
     consequently
    0.09
     accordingly
    0.09
    Activations Density 2.631%

    No Known Activations