© 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. 58825
    Prev
    Next
    INDEX
    Explanations

    types of stimulation

    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
    boro
    -0.12
    iken
    -0.11
     autop
    -0.10
    eming
    -0.10
    Credits
    -0.10
     Vog
    -0.10
    lyn
    -0.10
     Feather
    -0.10
    BOSE
    -0.10
     Hv
    -0.09
    POSITIVE LOGITS
    allet
    0.08
    udge
    0.07
     suit
    0.07
     Bench
    0.07
     aside
    0.07
     amid
    0.07
     pendant
    0.06
     :(
    0.06
     Rug
    0.06
    ầu
    0.06
    Activations Density 0.068%

    No Known Activations