© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2811
    Prev
    Next
    INDEX
    Explanations

    legal status, specific context

    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
     plais
    -0.12
     nouve
    -0.12
     siè
    -0.11
     réuss
    -0.10
     sorte
    -0.09
     rencontres
    -0.09
     meilleurs
    -0.09
     ê
    -0.09
     vite
    -0.08
     vieux
    -0.08
    POSITIVE LOGITS
     notably
    0.15
    forge
    0.12
     Philippe
    0.12
     Institut
    0.11
     Nicolas
    0.11
     Conse
    0.11
    .tp
    0.11
    Nb
    0.11
     Tours
    0.11
     Champ
    0.11
    Activations Density 0.942%

    No Known Activations