© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 61420
    Prev
    Next
    INDEX
    Explanations

    greeting tokens

    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
    Negative Logits
    ula
    -0.10
    tet
    -0.09
    unde
    -0.09
    onto
    -0.09
     Spicer
    -0.08
     seating
    -0.08
    tat
    -0.08
    -shared
    -0.08
    åĭ
    -0.08
     discussions
    -0.08
    POSITIVE LOGITS
     greet
    0.09
     caus
    0.08
    amic
    0.08
    roc
    0.08
    LEX
    0.08
    variably
    0.08
     Fa
    0.08
    Pending
    0.08
    vale
    0.08
    zens
    0.08
    Activations Density 0.022%

    No Known Activations