© 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. 2486
    Prev
    Next
    INDEX
    Explanations

    process and processing changes

    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
    _resources
    -0.09
    wel
    -0.09
    onis
    -0.09
     Aid
    -0.08
     incoming
    -0.08
     Cons
    -0.08
    onom
    -0.08
    payer
    -0.08
     Permanent
    -0.08
    ero
    -0.08
    POSITIVE LOGITS
     glue
    0.11
     timing
    0.10
     wield
    0.09
     Timing
    0.09
    Timing
    0.08
     accompanying
    0.08
     cab
    0.08
     pairing
    0.08
     Rules
    0.08
     wrapping
    0.08
    Activations Density 0.758%

    No Known Activations