© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3314
    Prev
    Next
    INDEX
    Explanations

    -ation / -ating results

    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
    ively
    -0.12
    ers
    -0.10
    arial
    -0.10
    ive
    -0.10
    dag
    -0.09
     Feinstein
    -0.09
    ingly
    -0.09
    olicited
    -0.09
    pel
    -0.09
    erton
    -0.09
    POSITIVE LOGITS
    ation
    0.29
    ated
    0.21
    ating
    0.19
    ATION
    0.18
    ATED
    0.16
    ations
    0.16
    ulation
    0.14
    iation
    0.13
    ination
    0.12
    INATION
    0.12
    Activations Density 0.355%

    No Known Activations