© 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. 4794
    Prev
    Next
    INDEX
    Explanations

    physical surfaces or layers

    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
     floating
    -0.08
     floats
    -0.08
     Hugh
    -0.08
     floated
    -0.08
    kj
    -0.07
     Lo
    -0.07
    amm
    -0.07
    Talking
    -0.07
    float
    -0.07
     central
    -0.07
    POSITIVE LOGITS
     surrounding
    0.17
     preceding
    0.11
    INGER
    0.11
    PRS
    0.11
     finger
    0.11
    ecided
    0.10
     adjacent
    0.10
     near
    0.10
    hog
    0.10
     outside
    0.10
    Activations Density 0.325%

    No Known Activations