© 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. 55290
    Prev
    Next
    INDEX
    Explanations

    var endings

    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
    ced
    -0.10
     Maver
    -0.10
    quis
    -0.08
     flash
    -0.08
    ained
    -0.08
    kul
    -0.08
     Dome
    -0.08
    endant
    -0.08
    лÑİ
    -0.08
    illi
    -0.08
    POSITIVE LOGITS
    nish
    0.11
    ees
    0.11
    eer
    0.10
    nal
    0.10
    ior
    0.10
    ible
    0.09
    rive
    0.09
    nings
    0.09
    ieg
    0.09
    ures
    0.09
    Activations Density 0.015%

    No Known Activations