© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    specific day or date

    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
     "...
    -0.09
     telephone
    -0.09
     presently
    -0.09
     telegram
    -0.08
     Welt
    -0.08
     automobile
    -0.08
     ath
    -0.08
     Graf
    -0.07
     furnishings
    -0.07
     Yugosl
    -0.07
    POSITIVE LOGITS
     Å
    0.14
     incentiv
    0.14
     Genius
    0.13
     surpr
    0.12
    engu
    0.11
     fridge
    0.11
    TM
    0.11
     quitting
    0.11
     recal
    0.10
     anyways
    0.10
    Activations Density 0.108%

    No Known Activations