© 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. 57952
    Prev
    Next
    INDEX
    Explanations

    evaluating quality or flaws

    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
    endale
    -0.12
    (compare
    -0.11
    berman
    -0.10
    arget
    -0.10
    ledge
    -0.10
    pus
    -0.10
    locate
    -0.10
    jac
    -0.10
     Arbor
    -0.10
     ("-
    -0.10
    POSITIVE LOGITS
     salvage
    0.08
     ferment
    0.08
     superior
    0.07
     chronological
    0.07
     overnight
    0.07
     Overnight
    0.07
     culmination
    0.07
     favored
    0.07
     mer
    0.07
     extr
    0.07
    Activations Density 0.049%

    No Known Activations