© 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. 3306
    Prev
    Next
    INDEX
    Explanations

    critical to

    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
    reply
    -0.09
    enco
    -0.08
     prote
    -0.08
    ario
    -0.08
    runner
    -0.08
     needing
    -0.08
    abant
    -0.08
    holder
    -0.08
    aces
    -0.08
    oose
    -0.08
    POSITIVE LOGITS
     success
    0.13
     survival
    0.10
     understanding
    0.10
    success
    0.10
     Success
    0.10
     correct
    0.09
     succès
    0.09
     Successful
    0.09
     maintaining
    0.09
     successful
    0.09
    Activations Density 0.204%

    No Known Activations