© 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. 58454
    Prev
    Next
    INDEX
    Explanations

    origin description phrases

    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
    cob
    -0.10
    uilder
    -0.10
     Cooler
    -0.10
    ource
    -0.09
    plat
    -0.09
     Gle
    -0.09
    ythe
    -0.09
     dripping
    -0.09
    omb
    -0.09
     belonged
    -0.09
    POSITIVE LOGITS
    Transform
    0.07
    transform
    0.07
    nel
    0.07
     float
    0.07
    ente
    0.07
     bran
    0.07
    ulo
    0.07
    ansi
    0.07
    azel
    0.07
     pang
    0.07
    Activations Density 0.113%

    No Known Activations