© 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. 4835
    Prev
    Next
    INDEX
    Explanations

    christ names

    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
    umin
    -0.09
    ster
    -0.09
    ibus
    -0.08
    rite
    -0.08
    jon
    -0.08
    imore
    -0.08
    STER
    -0.08
    otal
    -0.07
    åĬŁ
    -0.07
     pract
    -0.07
    POSITIVE LOGITS
    ensen
    0.10
     stranded
    0.10
    ophe
    0.10
    opher
    0.10
    loses
    0.09
    OLOR
    0.09
    pher
    0.09
    boards
    0.09
    opoulos
    0.09
     Christ
    0.09
    Activations Density 0.071%

    No Known Activations