© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    and followed by

    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
     Pin
    -0.07
    esa
    -0.07
     warns
    -0.07
     please
    -0.07
    iet
    -0.07
    ,it
    -0.07
    ån
    -0.07
    .calendar
    -0.07
    icut
    -0.07
    SDK
    -0.07
    POSITIVE LOGITS
     whose
    0.13
     whereby
    0.12
     wherein
    0.11
     which
    0.11
    which
    0.10
    whose
    0.10
     where
    0.10
     Somebody
    0.10
    because
    0.10
     коÑĤоÑĢ
    0.09
    Activations Density 0.303%

    No Known Activations