© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    programs, grants, and initiatives

    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
     Rentals
    -0.10
     logically
    -0.09
     stylist
    -0.09
    /configuration
    -0.09
     unchanged
    -0.09
    /layout
    -0.09
     Rankings
    -0.09
     INTERNAL
    -0.08
     inherited
    -0.08
     Notification
    -0.08
    POSITIVE LOGITS
     initiative
    0.18
     initiatives
    0.17
     outreach
    0.17
     program
    0.16
     project
    0.16
     aimed
    0.15
     volunte
    0.15
     Project
    0.15
     projects
    0.15
     programs
    0.15
    Activations Density 3.511%

    No Known Activations