© 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. 3331
    Prev
    Next
    INDEX
    Explanations

    millions of people worldwide

    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
    ozy
    -0.10
     overall
    -0.09
    иÑĦ
    -0.09
    ]){
    -0.09
     sogar
    -0.09
    istra
    -0.09
    zie
    -0.09
    odata
    -0.09
     disproportion
    -0.08
     Ster
    -0.08
    POSITIVE LOGITS
    bt
    0.08
     jan
    0.08
    semi
    0.08
    ette
    0.08
     band
    0.07
     dad
    0.07
     launder
    0.07
     worldwide
    0.07
    aran
    0.07
     supervised
    0.07
    Activations Density 0.155%

    No Known Activations