© 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. 4731
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    Not in Any Lists

    No Comments

    Negative Logits
     internals
    -0.10
    aco
    -0.09
    UTOR
    -0.09
    Challenge
    -0.09
    915
    -0.09
     Brooke
    -0.09
     toasted
    -0.09
    rin
    -0.09
    .Of
    -0.08
     Chess
    -0.08
    POSITIVE LOGITS
     correspondent
    0.09
    worthy
    0.09
     cess
    0.09
    usercontent
    0.09
    pii
    0.08
    olio
    0.08
    nal
    0.08
     Ree
    0.07
    alc
    0.07
    sole
    0.07
    Activations Density 0.098%

    No Known Activations