© 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. 53869
    Prev
    Next
    INDEX
    Explanations

    theorem statements

    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
    s
    -0.09
    enthal
    -0.09
    sar
    -0.08
     rare
    -0.08
    rite
    -0.07
    æĸĻ
    -0.07
    sand
    -0.07
    yh
    -0.07
    yyy
    -0.07
    eson
    -0.07
    POSITIVE LOGITS
     Crushers
    0.10
    .lu
    0.10
    atically
    0.10
    pler
    0.10
    ally
    0.10
    olia
    0.10
    ATIC
    0.10
     Peel
    0.10
    aram
    0.10
    OLID
    0.09
    Activations Density 0.003%

    No Known Activations