© 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. 58392
    Prev
    Next
    INDEX
    Explanations

    oil spills and nuclear accidents

    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
     Particip
    -0.09
    .sav
    -0.09
     phenomena
    -0.08
     redistributed
    -0.08
    elm
    -0.08
    åŁ
    -0.08
    æ®
    -0.08
    erm
    -0.08
     Saw
    -0.08
     randomly
    -0.08
    POSITIVE LOGITS
     spilled
    0.09
     spill
    0.09
     disg
    0.09
    uri
    0.09
    asu
    0.09
    kont
    0.08
     spills
    0.08
     Eff
    0.08
     eff
    0.08
     mish
    0.08
    Activations Density 0.043%

    No Known Activations