© 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. 4833
    Prev
    Next
    INDEX
    Explanations

    days and times

    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
    ë¦Ħ
    -0.10
     Flyers
    -0.10
     RSS
    -0.09
    ike
    -0.09
     Cutter
    -0.09
    angi
    -0.09
    hatt
    -0.09
    avanaugh
    -0.09
    MO
    -0.09
    /static
    -0.09
    POSITIVE LOGITS
    ardin
    0.09
    ions
    0.08
     reply
    0.08
    ridge
    0.08
     replies
    0.07
    ermann
    0.07
    isdiction
    0.07
    iphy
    0.07
     oblig
    0.07
     replied
    0.07
    Activations Density 0.066%

    No Known Activations