© 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. 54209
    Prev
    Next
    INDEX
    Explanations

    gaming traits and mechanics

    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
     confronting
    -0.11
    yte
    -0.11
     Vulkan
    -0.09
    itta
    -0.09
    eric
    -0.09
    zilla
    -0.08
    âĢº
    -0.08
    yang
    -0.08
    aise
    -0.08
    UTO
    -0.08
    POSITIVE LOGITS
     swallow
    0.10
     swallowed
    0.09
     effects
    0.09
     Effects
    0.09
     memberships
    0.09
     ogl
    0.09
    Effects
    0.09
    dup
    0.08
     affecting
    0.08
     Cascade
    0.08
    Activations Density 0.024%

    No Known Activations