© 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. 56767
    Prev
    Next
    INDEX
    Explanations

    evaluate, assess, investigate

    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
     clinically
    -0.08
     rightfully
    -0.08
    tas
    -0.08
     pediatric
    -0.08
     boarded
    -0.08
    mandatory
    -0.08
    heimer
    -0.07
     medical
    -0.07
    iais
    -0.07
     medically
    -0.07
    POSITIVE LOGITS
    Successful
    0.10
     Projects
    0.10
     successful
    0.10
     projects
    0.09
    ählen
    0.09
    illet
    0.09
     Successful
    0.09
    .libs
    0.09
    inear
    0.09
    ban
    0.09
    Activations Density 0.507%

    No Known Activations