© 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. 54302
    Prev
    Next
    INDEX
    Explanations

    low amounts or levels

    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
    aki
    -0.10
    nih
    -0.09
    quisition
    -0.09
    umber
    -0.09
    488
    -0.09
     synd
    -0.09
    cki
    -0.09
    enda
    -0.08
     Synd
    -0.08
     krist
    -0.08
    POSITIVE LOGITS
     negligible
    0.10
     fram
    0.09
    alias
    0.08
     impro
    0.08
    weak
    0.08
     tolerated
    0.08
     Peninsula
    0.08
     insignificant
    0.08
     circa
    0.08
     alias
    0.08
    Activations Density 0.100%

    No Known Activations