© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    solution, liquid, powder, paste, flux

    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
     Searching
    -0.08
     redis
    -0.08
     ensemble
    -0.08
    gage
    -0.08
    lide
    -0.08
     dissoci
    -0.08
     converters
    -0.08
     Slide
    -0.08
    Poll
    -0.08
     dust
    -0.08
    POSITIVE LOGITS
     During
    0.10
     during
    0.10
     Builder
    0.09
     Build
    0.09
     drafting
    0.09
     canv
    0.09
     Yok
    0.09
    CAA
    0.09
    onymous
    0.09
     build
    0.09
    Activations Density 0.583%

    No Known Activations