© 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. 4854
    Prev
    Next
    INDEX
    Explanations

    version, relative, amp, weak, www

    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
     Grat
    -0.09
    isson
    -0.08
     neb
    -0.08
     expelled
    -0.08
    enu
    -0.08
    cai
    -0.08
    atri
    -0.08
     bru
    -0.08
    guns
    -0.08
     tails
    -0.08
    POSITIVE LOGITS
     thereof
    0.09
     versions
    0.09
    pel
    0.09
     tou
    0.08
     version
    0.08
    arily
    0.08
    backend
    0.08
     Version
    0.08
     beside
    0.08
    uto
    0.08
    Activations Density 0.357%

    No Known Activations