© 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. 57770
    Prev
    Next
    INDEX
    Explanations

    units of measurement and quantities

    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
    cis
    -0.10
    cus
    -0.10
    tiny
    -0.09
    ointments
    -0.09
    ews
    -0.08
     tiny
    -0.08
     Recipes
    -0.08
     palette
    -0.08
     volta
    -0.08
     embr
    -0.08
    POSITIVE LOGITS
    plete
    0.10
     flock
    0.09
    otto
    0.09
    otti
    0.09
     keyst
    0.09
     rede
    0.08
     mesure
    0.08
     Nag
    0.08
     slicing
    0.08
     Cle
    0.08
    Activations Density 0.104%

    No Known Activations