© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    import statements or called

    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
     blinded
    -0.09
     gent
    -0.09
     sup
    -0.08
     Meg
    -0.08
     Dod
    -0.07
     bills
    -0.07
    管
    -0.07
     Pee
    -0.07
     Charl
    -0.07
    ulin
    -0.07
    POSITIVE LOGITS
    .Cloud
    0.08
    refix
    0.08
     saturation
    0.08
     Lifecycle
    0.08
     Rahman
    0.08
    ippy
    0.08
    oken
    0.08
     Quinn
    0.08
     getItemCount
    0.08
    favor
    0.08
    Activations Density 0.226%

    No Known Activations