© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    Both followed by groups, items, or conditions

    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
     Either
    -0.17
    either
    -0.16
     either
    -0.16
     EITHER
    -0.16
    Either
    -0.14
     BOTH
    -0.12
     alone
    -0.12
    Both
    -0.11
     Alone
    -0.11
     both
    -0.11
    POSITIVE LOGITS
     kinds
    0.08
    itz
    0.08
     Padding
    0.08
    agus
    0.08
     Kr
    0.08
    angi
    0.08
    itel
    0.07
     Cad
    0.07
    ran
    0.07
    kr
    0.07
    Activations Density 0.051%

    No Known Activations