© 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. 3581
    Prev
    Next
    INDEX
    Explanations

    judges in legal texts

    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
    asan
    -0.12
    *pow
    -0.11
     //_
    -0.10
     ofs
    -0.10
    aptcha
    -0.10
    unittest
    -0.10
     spo
    -0.10
    .Pay
    -0.10
    igin
    -0.10
     bon
    -0.09
    POSITIVE LOGITS
    ound
    0.08
    ulis
    0.07
     flesh
    0.07
     disabling
    0.07
     Ratings
    0.06
     stitched
    0.06
    AKER
    0.06
    alic
    0.06
    mes
    0.06
     Mess
    0.06
    Activations Density 0.002%

    No Known Activations