© 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. 56330
    Prev
    Next
    INDEX
    Explanations

    past participles

    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
     historically
    -0.12
    /is
    -0.08
     Cont
    -0.08
    .TestCase
    -0.08
     Hide
    -0.07
     evolves
    -0.07
     evolve
    -0.07
    ony
    -0.07
    ------+
    -0.07
    ysi
    -0.07
    POSITIVE LOGITS
    edin
    0.11
    've
    0.11
     has
    0.11
     have
    0.10
     HAS
    0.10
    -has
    0.10
    ’ve
    0.10
    _has
    0.10
    edd
    0.10
    azo
    0.09
    Activations Density 0.166%

    No Known Activations