© 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. 57547
    Prev
    Next
    INDEX
    Explanations

    chi-square and exact tests

    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
    eks
    -0.10
    lu
    -0.08
    itar
    -0.08
    äº
    -0.08
     Mus
    -0.07
     Ler
    -0.07
     schle
    -0.07
     banker
    -0.07
     porte
    -0.07
    bourne
    -0.07
    POSITIVE LOGITS
    rame
    0.10
    KY
    0.10
     rej
    0.09
     Hust
    0.09
     Stre
    0.09
    tion
    0.09
     Pir
    0.09
     cyst
    0.09
    RL
    0.09
    oken
    0.09
    Activations Density 0.020%

    No Known Activations