© 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. 2714
    Prev
    Next
    INDEX
    Explanations

    names or acronyms with suffixes

    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
    obb
    -0.09
    omap
    -0.09
     Playboy
    -0.09
    ¢åįķ
    -0.08
    peech
    -0.08
    oria
    -0.08
     rewarded
    -0.08
     INTERNAL
    -0.08
     courageous
    -0.08
     centrally
    -0.08
    POSITIVE LOGITS
    essim
    0.08
    uco
    0.08
     Overse
    0.08
    .mass
    0.08
    ente
    0.07
    0.07
     du
    0.07
     ÂŃ
    0.07
    lyph
    0.07
    gist
    0.07
    Activations Density 0.191%

    No Known Activations