© 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. 4403
    Prev
    Next
    INDEX
    Explanations

    learnings

    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
     Bowman
    -0.10
     Quantity
    -0.09
    unden
    -0.09
    hest
    -0.08
    -du
    -0.08
    acman
    -0.08
    еÑģÑĤв
    -0.08
     Oral
    -0.08
    535
    -0.08
     steady
    -0.08
    POSITIVE LOGITS
     Curve
    0.13
    Curve
    0.13
     curve
    0.11
     curves
    0.11
    ings
    0.11
    curve
    0.11
    ä¹
    0.10
    nings
    0.10
     kennen
    0.10
    -about
    0.09
    Activations Density 0.084%

    No Known Activations