© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    genuine affirmation

    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
     tuo
    -0.11
     but
    -0.11
    but
    -0.10
     only
    -0.10
     blasph
    -0.09
    ãģĹãģĭ
    -0.09
    gba
    -0.09
     Princip
    -0.09
    arest
    -0.09
     Only
    -0.09
    POSITIVE LOGITS
     legitimate
    0.15
     legitimately
    0.15
     indeed
    0.14
     genuine
    0.13
     certainly
    0.13
     undoubtedly
    0.11
     genuinely
    0.11
     duly
    0.11
     definitely
    0.11
    ç¡®
    0.11
    Activations Density 0.182%

    No Known Activations