© 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. 61198
    Prev
    Next
    INDEX
    Explanations

    component numbers

    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
    emit
    -0.10
     Herr
    -0.10
    andr
    -0.10
    ka
    -0.10
    amp
    -0.10
    AMP
    -0.09
     Alam
    -0.09
     Massive
    -0.09
    KA
    -0.09
     Bray
    -0.09
    POSITIVE LOGITS
    RSS
    0.08
     optionally
    0.08
    eon
    0.07
    ?a
    0.07
    shore
    0.07
     breathed
    0.07
     ren
    0.07
     doubly
    0.07
    itti
    0.07
     Mong
    0.07
    Activations Density 0.007%

    No Known Activations