© 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. 819
    Prev
    Next
    INDEX
    Explanations

    state, condition, or concept

    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
     geared
    -0.10
     Restr
    -0.08
    .eql
    -0.08
     decking
    -0.08
    ansi
    -0.08
     regarding
    -0.08
    853
    -0.08
     involved
    -0.08
    áºŃn
    -0.08
    wers
    -0.08
    POSITIVE LOGITS
     everywhere
    0.10
     separate
    0.09
     elsewhere
    0.09
     somewhere
    0.09
     happening
    0.09
     Wid
    0.09
    ãģ¾
    0.09
     unnoticed
    0.09
     prominently
    0.09
     everyday
    0.09
    Activations Density 3.052%

    No Known Activations