© 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. 61804
    Prev
    Next
    INDEX
    Explanations

    size and thickness settings

    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
     Curt
    -0.10
    -material
    -0.10
    /Gate
    -0.10
     diversity
    -0.10
    bow
    -0.09
    igers
    -0.09
    (sync
    -0.09
    /null
    -0.09
    ä¿
    -0.09
    targets
    -0.09
    POSITIVE LOGITS
    isses
    0.08
     Marin
    0.07
    Drv
    0.07
    yles
    0.07
    dos
    0.07
     Stan
    0.07
     Desc
    0.07
     che
    0.07
     transpose
    0.06
     Dos
    0.06
    Activations Density 0.002%

    No Known Activations