© 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. 58963
    Prev
    Next
    INDEX
    Explanations

    applications open or accepted

    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
     imap
    -0.11
    anten
    -0.10
     hurd
    -0.10
     plan
    -0.10
     preempt
    -0.09
     booking
    -0.09
     Henrik
    -0.09
     embar
    -0.09
    illon
    -0.09
     Bark
    -0.09
    POSITIVE LOGITS
    ICT
    0.09
    andler
    0.09
    ksam
    0.08
    lect
    0.08
    vard
    0.08
     contro
    0.08
     BaÅŁ
    0.08
     till
    0.07
     æķ
    0.07
     recess
    0.07
    Activations Density 0.061%

    No Known Activations