© 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. 61153
    Prev
    Next
    INDEX
    Explanations

    tag questions seeking confirmation

    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
     Emm
    -0.09
     Elis
    -0.08
     Schneider
    -0.08
     sno
    -0.07
    enge
    -0.07
    antas
    -0.07
     barred
    -0.07
     Garrett
    -0.07
     spin
    -0.07
    ikel
    -0.07
    POSITIVE LOGITS
     ðŁĺī
    0.11
     ERA
    0.11
    /New
    0.11
    alia
    0.10
    coles
    0.10
    bulan
    0.09
    obody
    0.09
    sek
    0.09
    /import
    0.09
    olumn
    0.09
    Activations Density 0.012%

    No Known Activations