© 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. 61183
    Prev
    Next
    INDEX
    Explanations

    remaining or exceptions

    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
    ÑĪ
    -0.09
    checker
    -0.09
    ARK
    -0.09
    ún
    -0.09
    -Core
    -0.09
    angan
    -0.08
    ordinary
    -0.08
    ESS
    -0.08
     outra
    -0.08
    assi
    -0.08
    POSITIVE LOGITS
     exceptions
    0.17
     Exceptions
    0.15
     remaining
    0.15
    Exceptions
    0.13
    Remaining
    0.13
     Remaining
    0.13
     exception
    0.12
    remaining
    0.10
     remainder
    0.10
     occasionally
    0.10
    Activations Density 0.160%

    No Known Activations