© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    titles, suffixes, and names

    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
    Advertis
    -0.08
     spl
    -0.07
     stre
    -0.07
    Putin
    -0.07
    sville
    -0.07
    imar
    -0.07
    çĶ±
    -0.07
     yourselves
    -0.07
    åĵ
    -0.07
    ikon
    -0.07
    POSITIVE LOGITS
     Jr
    0.30
     jr
    0.19
     aka
    0.18
     Sr
    0.17
     alias
    0.15
     PhD
    0.13
    âĢİ
    0.12
     who
    0.11
     JR
    0.11
    aka
    0.11
    Activations Density 1.673%

    No Known Activations