© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    called, named, or termed

    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
     Pill
    -0.07
    ulla
    -0.07
    pp
    -0.07
    pac
    -0.07
     Spi
    -0.07
     ho
    -0.06
     horns
    -0.06
     pancre
    -0.06
     Hoy
    -0.06
    aggi
    -0.06
    POSITIVE LOGITS
     termed
    0.15
     terminology
    0.14
    称
    0.14
     collo
    0.13
     whatever
    0.12
     referred
    0.12
     called
    0.12
     Called
    0.12
     term
    0.12
     whichever
    0.12
    Activations Density 0.209%

    No Known Activations