© 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. 53834
    Prev
    Next
    INDEX
    Explanations

    line separators and following text

    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
    ĵ
    -0.08
     Tob
    -0.08
     kole
    -0.08
     Bent
    -0.07
     rever
    -0.07
    anz
    -0.07
    eron
    -0.07
    aban
    -0.07
    nist
    -0.07
    ãģĹãģĭ
    -0.07
    POSITIVE LOGITS
     Suff
    0.11
    endor
    0.10
    oola
    0.10
     suffice
    0.09
    tha
    0.09
    ita
    0.09
     ambit
    0.09
    iland
    0.09
    (if
    0.09
     gou
    0.09
    Activations Density 0.016%

    No Known Activations