© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3268
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and decisions

    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
     retro
    -0.12
     Retro
    -0.09
     reconstruction
    -0.08
    ло
    -0.08
     Remaining
    -0.08
     rebuild
    -0.08
     retrospective
    -0.08
     Reconstruction
    -0.07
     suddenly
    -0.07
     irreversible
    -0.07
    POSITIVE LOGITS
    inerary
    0.11
    ews
    0.11
    ajo
    0.10
     progresses
    0.10
     Pompe
    0.10
    verity
    0.10
     selective
    0.09
     Laud
    0.09
    EDIA
    0.09
     bog
    0.09
    Activations Density 0.059%

    No Known Activations