© 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. 55927
    Prev
    Next
    INDEX
    Explanations

    said, added, informs, pe

    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
     critically
    -0.10
    {Name
    -0.08
    elay
    -0.08
     yell
    -0.08
     blasting
    -0.08
     barr
    -0.08
    \u
    -0.08
    GBP
    -0.08
     crim
    -0.08
    UBL
    -0.08
    POSITIVE LOGITS
     tentative
    0.09
     holes
    0.09
    veh
    0.08
     Miner
    0.08
    éĥ¨
    0.08
     feeder
    0.08
    ugen
    0.08
    noinspection
    0.08
    ppe
    0.08
    simp
    0.08
    Activations Density 0.002%

    No Known Activations