© 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. 58834
    Prev
    Next
    INDEX
    Explanations

    Jud followed by endings like ah, i, son, ging

    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
    itional
    -0.10
    yen
    -0.09
    uncture
    -0.09
    ournals
    -0.08
    room
    -0.08
    inue
    -0.08
    iams
    -0.07
    rome
    -0.07
    bons
    -0.07
    een
    -0.07
    POSITIVE LOGITS
    iser
    0.10
    ging
    0.09
    gmt
    0.09
    etime
    0.09
     Randall
    0.09
    ness
    0.09
     gob
    0.09
    ario
    0.08
    åŃĹ
    0.08
    /false
    0.08
    Activations Density 0.003%

    No Known Activations