© 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. 56083
    Prev
    Next
    INDEX
    Explanations

    `org.` followed by package names

    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
    izo
    -0.10
     Haj
    -0.10
    anker
    -0.09
     Crab
    -0.09
    ppo
    -0.09
    YPD
    -0.08
     Crash
    -0.08
     disgu
    -0.08
     Erl
    -0.08
    -be
    -0.08
    POSITIVE LOGITS
     fre
    0.08
    angel
    0.07
     Borg
    0.07
    olas
    0.07
     Benton
    0.07
    ense
    0.07
    jk
    0.07
    guarded
    0.07
    )._
    0.07
     Barker
    0.07
    Activations Density 0.003%

    No Known Activations