© 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. 55784
    Prev
    Next
    INDEX
    Explanations

    Copyright or section titles

    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
     Recorder
    -0.08
    (
    -0.08
    ol
    -0.08
    agra
    -0.08
    assen
    -0.08
     bol
    -0.07
     Jes
    -0.07
    owl
    -0.07
     buses
    -0.07
     McD
    -0.07
    POSITIVE LOGITS
    din
    0.12
     sai
    0.11
    emale
    0.10
    anan
    0.10
    oud
    0.10
    ymi
    0.10
    tti
    0.09
    ewe
    0.09
    aging
    0.09
    erring
    0.09
    Activations Density 0.001%

    No Known Activations