© 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. 4187
    Prev
    Next
    INDEX
    Explanations

    created, abolished, merged, split

    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
    sell
    -0.10
    rans
    -0.10
    radi
    -0.09
     Hoy
    -0.09
     )[
    -0.09
    mit
    -0.09
    Contr
    -0.09
    åĭ
    -0.09
    ipp
    -0.09
    sr
    -0.09
    POSITIVE LOGITS
     merger
    0.11
     merged
    0.11
     split
    0.11
     merge
    0.10
     merging
    0.10
    -split
    0.10
     Separate
    0.09
     separate
    0.09
     splits
    0.09
     carved
    0.09
    Activations Density 0.304%

    No Known Activations