© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    legal and official actions

    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
     (("
    -0.10
     nineteen
    -0.09
    ,the
    -0.09
     versus
    -0.09
     (“
    -0.08
     governmental
    -0.08
     thirteen
    -0.08
    indered
    -0.08
     ={
    -0.08
     goalt
    -0.08
    POSITIVE LOGITS
     '
    0.12
     intl
    0.11
     docs
    0.10
     Dems
    0.10
     '[
    0.10
     Dept
    0.10
    bout
    0.10
     Docs
    0.10
     prof
    0.10
    -'
    0.10
    Activations Density 1.108%

    No Known Activations