© 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. 4228
    Prev
    Next
    INDEX
    Explanations

    function call syntax

    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
     traps
    -0.09
     fatt
    -0.09
     Tw
    -0.09
     MIS
    -0.08
     recovery
    -0.08
    ÙĦا
    -0.08
     trap
    -0.08
     escap
    -0.08
     trapping
    -0.08
    heim
    -0.08
    POSITIVE LOGITS
    È
    0.09
    -article
    0.09
    ez
    0.08
     SPDX
    0.08
    velt
    0.08
    ikit
    0.08
    stre
    0.08
    neo
    0.08
    AMI
    0.08
     ram
    0.08
    Activations Density 0.576%

    No Known Activations