© 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. 57292
    Prev
    Next
    INDEX
    Explanations

    becoming more popular

    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
     Industrial
    -0.10
     accr
    -0.09
     analy
    -0.09
    nin
    -0.09
     ushort
    -0.09
     Worse
    -0.09
     Redistribution
    -0.08
     managers
    -0.08
     Ce
    -0.08
    Ce
    -0.08
    POSITIVE LOGITS
     popularity
    0.10
     appeal
    0.10
     appealing
    0.09
    arkan
    0.09
     soared
    0.09
     trend
    0.08
     accessibility
    0.08
     relieve
    0.08
    -bars
    0.08
     motivations
    0.08
    Activations Density 0.101%

    No Known Activations