© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    nested structures or chains

    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
    idle
    -0.08
    iman
    -0.08
     Nearby
    -0.08
    lij
    -0.07
    usu
    -0.07
     discre
    -0.07
     simultaneous
    -0.07
    vid
    -0.07
     Feld
    -0.07
    ium
    -0.07
    POSITIVE LOGITS
     nested
    0.21
     recursively
    0.18
     further
    0.17
     hier
    0.17
     layers
    0.16
     Nested
    0.16
     chain
    0.16
     chained
    0.16
     layer
    0.16
     deeper
    0.16
    Activations Density 2.149%

    No Known Activations