© 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. 61194
    Prev
    Next
    INDEX
    Explanations

    clinical trials

    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
    .tp
    -0.12
    reste
    -0.12
    avr
    -0.11
    cri
    -0.11
     imper
    -0.11
    BUG
    -0.11
    capt
    -0.11
     StringComparison
    -0.11
    plr
    -0.11
     babys
    -0.11
    POSITIVE LOGITS
     levels
    0.07
     coin
    0.06
     gr
    0.06
    ulus
    0.06
    es
    0.06
    иÑĢов
    0.06
     Trust
    0.06
     upwards
    0.05
    omer
    0.05
     Gemini
    0.05
    Activations Density 0.028%

    No Known Activations