© 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. 53942
    Prev
    Next
    INDEX
    Explanations

    Proceedings of conferences

    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
    rega
    -0.09
    hex
    -0.09
    aida
    -0.09
    ics
    -0.09
    lined
    -0.08
    etus
    -0.08
     placer
    -0.08
    cala
    -0.08
    yal
    -0.08
    sem
    -0.08
    POSITIVE LOGITS
    alo
    0.09
     Appeals
    0.08
    lector
    0.08
    aho
    0.08
     Alone
    0.08
     Armed
    0.07
     Meetings
    0.07
     Archer
    0.07
    ahoma
    0.07
     Cart
    0.07
    Activations Density 0.003%

    No Known Activations