© 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. 598
    Prev
    Next
    INDEX
    Explanations

    affects properties

    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
    .ToShort
    -0.09
     greater
    -0.08
     versatile
    -0.08
     scalable
    -0.08
     phenomenon
    -0.08
     tremendous
    -0.08
     double
    -0.08
     remarkable
    -0.08
     great
    -0.07
    persistent
    -0.07
    POSITIVE LOGITS
     overall
    0.22
     amount
    0.19
     number
    0.16
     perceived
    0.16
     size
    0.15
     frequency
    0.14
     aggress
    0.14
     length
    0.14
     levels
    0.14
     quality
    0.13
    Activations Density 2.681%

    No Known Activations