© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
     rek
    -0.10
     jt
    -0.09
     jd
    -0.09
     zach
    -0.09
     pj
    -0.09
     pij
    -0.09
     baj
    -0.09
     menn
    -0.08
     Sle
    -0.08
     gord
    -0.08
    POSITIVE LOGITS
     unnamed
    0.10
    *K
    0.09
    another
    0.09
    <"
    0.09
     unidentified
    0.09
    ¡°
    0.09
     another
    0.09
     '%'
    0.09
     enviado
    0.09
     teil
    0.09
    Activations Density 1.746%

    No Known Activations