© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    reduces cost or damage

    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
    leo
    -0.09
     strategies
    -0.09
    game
    -0.09
    lich
    -0.08
     strategy
    -0.08
     game
    -0.07
     orbs
    -0.07
     tactics
    -0.07
     Strategies
    -0.07
     Strategy
    -0.07
    POSITIVE LOGITS
    osi
    0.10
    verts
    0.10
     halves
    0.10
     hal
    0.10
     íļĮ
    0.10
     roll
    0.10
     half
    0.10
     ((_
    0.10
    bek
    0.10
     reduces
    0.09
    Activations Density 0.085%

    No Known Activations