© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    classical, material, nuclear, civil, print, imperative

    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
    onas
    -0.08
    inas
    -0.08
    oul
    -0.08
     Holocaust
    -0.07
     holog
    -0.07
     abroad
    -0.07
    ampus
    -0.07
    hana
    -0.06
     otherwise
    -0.06
    han
    -0.06
    POSITIVE LOGITS
     counterparts
    0.16
     counterpart
    0.14
     equivalents
    0.12
     Equivalent
    0.12
     Briggs
    0.11
     equivalent
    0.11
    Filed
    0.10
     Toxic
    0.10
     pare
    0.10
    andom
    0.10
    Activations Density 0.424%

    No Known Activations