© 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. 58292
    Prev
    Next
    INDEX
    Explanations

    after or when

    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
     Finding
    -0.10
     finding
    -0.10
     Successfully
    -0.10
     Morm
    -0.10
     successful
    -0.09
     Successful
    -0.09
     envision
    -0.09
     Narrow
    -0.09
     Neck
    -0.09
     victorious
    -0.09
    POSITIVE LOGITS
     direct
    0.09
     invested
    0.09
     efforts
    0.09
     effort
    0.09
    bat
    0.09
     bat
    0.09
     Kontakt
    0.08
    touch
    0.08
     nonatomic
    0.08
     contacted
    0.08
    Activations Density 0.156%

    No Known Activations