© 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. 57816
    Prev
    Next
    INDEX
    Explanations

    conflict and survival outcomes

    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
     placeholder
    -0.07
    selling
    -0.07
     Grip
    -0.07
    606
    -0.07
     unpublished
    -0.07
     Gins
    -0.07
     transparency
    -0.07
    pert
    -0.07
    Destination
    -0.07
    pcm
    -0.06
    POSITIVE LOGITS
     confront
    0.12
     situations
    0.12
     outnumber
    0.11
     confrontation
    0.11
     du
    0.11
    ffen
    0.10
     surviv
    0.10
     sie
    0.10
     chor
    0.10
     butcher
    0.10
    Activations Density 0.033%

    No Known Activations