© 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. 61887
    Prev
    Next
    INDEX
    Explanations

    clause enumeration (a), (A), (I), (II)

    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
    ewise
    -0.11
    IDEO
    -0.10
    pedo
    -0.10
    Ŀ
    -0.10
    .El
    -0.10
    roupon
    -0.10
    .Prot
    -0.10
    iband
    -0.09
    itra
    -0.09
     righteous
    -0.09
    POSITIVE LOGITS
    Happy
    0.08
     Happ
    0.07
     Rosenberg
    0.07
     Proud
    0.06
     reli
    0.06
     Kore
    0.06
     sat
    0.06
    QueryString
    0.06
    Weapons
    0.06
    bb
    0.06
    Activations Density 0.009%

    No Known Activations