© 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. 56571
    Prev
    Next
    INDEX
    Explanations

    injury and misfortune

    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
    forge
    -0.12
    .github
    -0.10
    Ùī
    -0.09
    <quote
    -0.09
    owitz
    -0.09
     Gast
    -0.09
     urg
    -0.09
    ergus
    -0.09
    º
    -0.09
    ninger
    -0.09
    POSITIVE LOGITS
     cursed
    0.10
     curse
    0.09
     curses
    0.09
     unlucky
    0.08
     victim
    0.08
    jid
    0.08
     soph
    0.08
     housed
    0.07
     supports
    0.07
     graduation
    0.07
    Activations Density 0.009%

    No Known Activations