© 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. 54027
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and derivatives

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sweep
    -0.08
     Sweep
    -0.07
    elf
    -0.07
     ex
    -0.07
    u
    -0.07
     Kap
    -0.07
    ugal
    -0.07
    wel
    -0.07
     Pole
    -0.07
     Char
    -0.07
    POSITIVE LOGITS
     Salv
    0.09
    ç©
    0.09
     slo
    0.09
    Č↵
    0.09
     jun
    0.09
     salv
    0.09
    gli
    0.09
    .cx
    0.09
    erca
    0.08
     sodom
    0.08
    Activations Density 0.002%

    No Known Activations