© 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. 8403
    Prev
    Next
    INDEX
    Explanations

    wisdom, lessons, or advice

    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
     fantasies
    -0.10
     Documentation
    -0.10
     Docs
    -0.09
     Fant
    -0.09
    jt
    -0.09
     DOC
    -0.09
    ,ev
    -0.09
    aux
    -0.09
     stav
    -0.09
    ounty
    -0.09
    POSITIVE LOGITS
     lesson
    0.18
     lessons
    0.17
     Lessons
    0.17
     Lesson
    0.16
     wisdom
    0.13
     advice
    0.13
    Lesson
    0.13
    lessons
    0.13
     admon
    0.12
     advises
    0.12
    Activations Density 0.341%

    No Known Activations