© 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. 8824
    Prev
    Next
    INDEX
    Explanations

    recommendation or review

    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
    Negative Logits
     tamp
    -0.10
     realistically
    -0.09
     aspirations
    -0.09
    alse
    -0.09
     panic
    -0.09
     dreams
    -0.09
     rear
    -0.08
     inherit
    -0.08
     panicked
    -0.08
     Tes
    -0.08
    POSITIVE LOGITS
     recommendation
    0.15
     Recommendation
    0.13
     recommended
    0.12
     recommending
    0.12
     recommend
    0.12
     Recomm
    0.11
     recommends
    0.11
     recommendations
    0.11
     recomend
    0.11
     spoilers
    0.10
    Activations Density 0.315%

    No Known Activations