© 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. 3793
    Prev
    Next
    INDEX
    Explanations

    role or cause

    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
    due
    -0.09
    walker
    -0.09
     Hawk
    -0.09
     react
    -0.09
     due
    -0.09
    uest
    -0.08
    Due
    -0.08
     reaction
    -0.08
     inexp
    -0.08
    stem
    -0.08
    POSITIVE LOGITS
     contributing
    0.16
    contrib
    0.15
     contribute
    0.14
     contributes
    0.14
     explaining
    0.13
     Contributor
    0.13
     contribution
    0.13
     contrib
    0.13
     contributions
    0.13
     Contributions
    0.13
    Activations Density 0.414%

    No Known Activations