© 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. 3622
    Prev
    Next
    INDEX
    Explanations

    math/science notation or terms

    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
     deb
    -0.10
     debating
    -0.10
    riter
    -0.10
    Pear
    -0.10
    ovel
    -0.10
     Bou
    -0.10
     Tol
    -0.09
     Baron
    -0.09
    'b
    -0.09
     bis
    -0.09
    POSITIVE LOGITS
    licht
    0.08
    ulis
    0.08
    avar
    0.08
     Knot
    0.08
     alan
    0.08
     rings
    0.07
    sse
    0.07
    usat
    0.07
     underlying
    0.07
     Rational
    0.07
    Activations Density 0.653%

    No Known Activations