© 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. 1502
    Prev
    Next
    INDEX
    Explanations

    purposes and future plans

    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
    ombat
    -0.10
    coil
    -0.09
     fores
    -0.09
     Arr
    -0.09
     commodities
    -0.09
    engo
    -0.08
    zas
    -0.08
    anguage
    -0.08
    preter
    -0.08
     lobbyist
    -0.08
    POSITIVE LOGITS
     later
    0.17
     purposes
    0.17
     future
    0.16
    later
    0.14
     eventual
    0.14
     subsequent
    0.14
     further
    0.12
     upcoming
    0.12
    Later
    0.12
    future
    0.11
    Activations Density 2.324%

    No Known Activations