© 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. 57756
    Prev
    Next
    INDEX
    Explanations

    rivalry and competition

    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
    quiv
    -0.10
    unter
    -0.10
    lle
    -0.09
    alion
    -0.09
    [out
    -0.09
     ward
    -0.09
    baugh
    -0.08
     taxable
    -0.08
    iah
    -0.08
     ante
    -0.08
    POSITIVE LOGITS
    ries
    0.17
    rous
    0.14
    rosse
    0.09
    lops
    0.09
    led
    0.08
    pled
    0.08
     blends
    0.08
    Sense
    0.08
    than
    0.08
    rie
    0.08
    Activations Density 0.005%

    No Known Activations