© 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. 53916
    Prev
    Next
    INDEX
    Explanations

    COURT OF

    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
     Locker
    -0.08
    PU
    -0.08
    onaut
    -0.07
    CS
    -0.07
     Celtic
    -0.07
     pratic
    -0.07
     fakt
    -0.07
     aque
    -0.07
    .How
    -0.07
    winner
    -0.07
    POSITIVE LOGITS
    irim
    0.10
     jam
    0.10
    Jam
    0.09
    uel
    0.09
    ideo
    0.09
    jac
    0.08
    æĿ
    0.08
     recogn
    0.08
    lex
    0.08
    plex
    0.08
    Activations Density 0.005%

    No Known Activations