© 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. 57954
    Prev
    Next
    INDEX
    Explanations

    hypothesis testing

    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
    obot
    -0.08
     Tea
    -0.08
     jot
    -0.08
     Simon
    -0.08
    óż
    -0.07
    coc
    -0.07
     cricket
    -0.07
    arrera
    -0.07
     Bryant
    -0.07
    .ph
    -0.07
    POSITIVE LOGITS
     odds
    0.11
     McB
    0.10
     selfish
    0.10
     seeding
    0.10
     Binding
    0.09
    elin
    0.09
    hone
    0.09
     Surv
    0.09
    chem
    0.09
    -binding
    0.09
    Activations Density 0.026%

    No Known Activations