© 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. 4155
    Prev
    Next
    INDEX
    Explanations

    minimize or prevent

    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
     accordingly
    -0.09
     ↵↵↵↵
    -0.08
     remarkably
    -0.08
     lightweight
    -0.08
    hawks
    -0.08
     Lightweight
    -0.08
    ellan
    -0.08
    needs
    -0.07
    &amp
    -0.07
     Needs
    -0.07
    POSITIVE LOGITS
     Scrap
    0.09
    reme
    0.09
     Flux
    0.09
    133
    0.08
     easier
    0.08
    ink
    0.08
     emphasis
    0.08
     Union
    0.08
    uster
    0.08
     stom
    0.08
    Activations Density 0.266%

    No Known Activations