© 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. 8195
    Prev
    Next
    INDEX
    Explanations

    comprising and means

    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
    he
    -0.07
    pron
    -0.07
    frame
    -0.07
     Sou
    -0.07
     lag
    -0.07
     Cher
    -0.07
     sandy
    -0.07
    из
    -0.06
     Dresden
    -0.06
     routine
    -0.06
    POSITIVE LOGITS
    /high
    0.11
    ulas
    0.10
     Ones
    0.10
    gles
    0.10
    .ElementAt
    0.09
    afen
    0.09
    bias
    0.09
    677
    0.09
     sÃŃ
    0.09
    aux
    0.09
    Activations Density 1.310%

    No Known Activations