© 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. 4221
    Prev
    Next
    INDEX
    Explanations

    Islam

    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
    pei
    -0.10
     Vish
    -0.09
     Mahar
    -0.09
    rss
    -0.09
    alter
    -0.09
     Dong
    -0.09
    lei
    -0.09
     Vet
    -0.09
    è¾
    -0.09
     Krish
    -0.09
    POSITIVE LOGITS
    uzz
    0.11
    edin
    0.10
    udd
    0.10
    pour
    0.10
    ż
    0.10
     shar
    0.09
     Hus
    0.09
    abad
    0.09
     iq
    0.09
     al
    0.09
    Activations Density 0.632%

    No Known Activations