© 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. 56599
    Prev
    Next
    INDEX
    Explanations

    jewelry and jewellery

    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
    cl
    -0.12
     clad
    -0.11
     sheets
    -0.10
    ego
    -0.09
     stad
    -0.09
    uniform
    -0.09
     plates
    -0.09
     Rid
    -0.09
     PAC
    -0.09
    ATO
    -0.09
    POSITIVE LOGITS
    /watch
    0.10
     jew
    0.09
    orges
    0.09
     Jewelry
    0.09
     jewellery
    0.08
    pora
    0.08
     eyed
    0.08
    hip
    0.08
     Fallon
    0.08
    dbo
    0.08
    Activations Density 0.021%

    No Known Activations