© 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. 61660
    Prev
    Next
    INDEX
    Explanations

    challenging or complex materials

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Gerr
    -0.08
    imed
    -0.07
    086
    -0.07
     intentionally
    -0.07
    jt
    -0.07
    ай
    -0.07
     TBD
    -0.07
     Kara
    -0.07
     Furn
    -0.07
    elt
    -0.07
    POSITIVE LOGITS
     elusive
    0.10
     slippery
    0.10
    xor
    0.10
     challenging
    0.10
     notoriously
    0.10
    pac
    0.10
     exotic
    0.10
     mediums
    0.10
     complexities
    0.09
     Difficulty
    0.09
    Activations Density 0.125%

    No Known Activations