© 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. 8270
    Prev
    Next
    INDEX
    Explanations

    gene expression activation

    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
    agua
    -0.10
    _spell
    -0.09
     incontr
    -0.09
    060
    -0.09
     plum
    -0.09
    rush
    -0.08
    INCLUDE
    -0.08
    pons
    -0.08
     spells
    -0.08
     buzz
    -0.08
    POSITIVE LOGITS
     Gym
    0.09
     Cad
    0.08
     hesitate
    0.08
    lad
    0.07
     Gos
    0.07
     DAL
    0.07
     anda
    0.07
     gauche
    0.07
     elseif
    0.07
     himself
    0.07
    Activations Density 0.203%

    No Known Activations