© 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. 58058
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    oen
    -0.11
     occasion
    -0.09
    retty
    -0.09
     sens
    -0.09
    iniz
    -0.09
    baby
    -0.09
    qual
    -0.09
    bos
    -0.09
     Bab
    -0.09
    ement
    -0.09
    POSITIVE LOGITS
     scrapped
    0.08
    .rabbit
    0.08
    eron
    0.07
    ola
    0.07
     Gast
    0.07
    otel
    0.07
     Jacobs
    0.07
    654
    0.07
     GOT
    0.07
     spoke
    0.07
    Activations Density 0.068%

    No Known Activations