© 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. 1050
    Prev
    Next
    INDEX
    Explanations

    'm and 're contractions

    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
     drunken
    -0.11
     sparking
    -0.10
     exaggerated
    -0.10
     arous
    -0.09
     improvised
    -0.09
     penetrating
    -0.09
     shared
    -0.09
    owering
    -0.09
     knowing
    -0.08
     defeating
    -0.08
    POSITIVE LOGITS
     able
    0.19
    /am
    0.15
    /we
    0.14
     glad
    0.14
     lucky
    0.13
     supposed
    0.13
     sure
    0.13
     planning
    0.13
     groot
    0.13
     gonna
    0.13
    Activations Density 1.107%

    No Known Activations