© 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. 57928
    Prev
    Next
    INDEX
    Explanations

    first names preceding last names

    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
    举
    -0.11
    moth
    -0.11
     wil
    -0.10
    vic
    -0.10
     hinge
    -0.09
    174
    -0.09
    nts
    -0.09
    óa
    -0.09
    contin
    -0.09
     smith
    -0.09
    POSITIVE LOGITS
    uxe
    0.06
    arkin
    0.06
    bai
    0.06
    ány
    0.06
     pref
    0.06
     inv
    0.06
     mnemonic
    0.06
     badge
    0.06
    ourney
    0.06
     promin
    0.06
    Activations Density 0.015%

    No Known Activations