© 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. 61156
    Prev
    Next
    INDEX
    Explanations

    national or conference titles

    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
    )._
    -0.10
    epar
    -0.10
    LEGRO
    -0.09
    TAG
    -0.09
    tog
    -0.09
     TOUCH
    -0.09
    usi
    -0.09
    cline
    -0.09
     edition
    -0.09
    propri
    -0.09
    POSITIVE LOGITS
     toast
    0.07
     Davidson
    0.07
    al
    0.07
     privileged
    0.07
    ob
    0.07
     Fisher
    0.07
     derives
    0.07
     Shades
    0.06
     íķĦ
    0.06
    assembly
    0.06
    Activations Density 0.058%

    No Known Activations