© 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. 54386
    Prev
    Next
    INDEX
    Explanations

    isLastChild, IsProcessed, isDebug, isServer

    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
    IfNeeded
    -0.11
    arra
    -0.10
    zet
    -0.10
     dumps
    -0.10
    onesia
    -0.10
     staged
    -0.09
    rij
    -0.09
     stripper
    -0.09
     Orb
    -0.09
    eel
    -0.09
    POSITIVE LOGITS
    omorphic
    0.08
     relent
    0.07
    oola
    0.07
     depends
    0.07
    endpoint
    0.07
    atically
    0.07
    ively
    0.06
     conveyed
    0.06
     likely
    0.06
    æļ
    0.06
    Activations Density 0.027%

    No Known Activations