© 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. 56860
    Prev
    Next
    INDEX
    Explanations

    parenthetical lists

    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
     cle
    -0.07
     pr
    -0.07
    ho
    -0.06
    Vault
    -0.06
    BO
    -0.06
     parl
    -0.06
    es
    -0.06
    ady
    -0.06
    okes
    -0.06
     Mos
    -0.06
    POSITIVE LOGITS
    canf
    0.10
    aland
    0.10
    jam
    0.10
    .pin
    0.09
     cork
    0.09
    eer
    0.09
    burgh
    0.09
    leh
    0.09
    ilestone
    0.09
    pin
    0.09
    Activations Density 0.003%

    No Known Activations