© 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. 54067
    Prev
    Next
    INDEX
    Explanations

    matter and properties

    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
    atory
    -0.10
    spm
    -0.09
     pace
    -0.09
    TY
    -0.09
    ®
    -0.09
    UA
    -0.08
    inery
    -0.08
     gal
    -0.08
    ).__
    -0.08
    amespace
    -0.08
    POSITIVE LOGITS
    igli
    0.09
    entin
    0.09
    LESS
    0.09
    ixer
    0.09
    leigh
    0.09
    gem
    0.08
    iers
    0.08
    ele
    0.08
    nicos
    0.08
    egan
    0.08
    Activations Density 0.003%

    No Known Activations