© 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. 8145
    Prev
    Next
    INDEX
    Explanations

    names ending in -ek, -kad, -sek, -nel, -vall, -vad, -ses, -ag, -kov

    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
    er
    -0.14
    en
    -0.14
    lehem
    -0.10
    eria
    -0.09
    åĻ¨
    -0.09
     bufsize
    -0.09
    uez
    -0.09
    erate
    -0.09
     Dal
    -0.08
    dbg
    -0.08
    POSITIVE LOGITS
    ĺìĿ´
    0.10
    pack
    0.09
    nie
    0.08
    cad
    0.08
    ionic
    0.08
     Bradford
    0.08
    owie
    0.08
    ted
    0.08
    ingly
    0.08
    lash
    0.08
    Activations Density 0.595%

    No Known Activations