© 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. 4744
    Prev
    Next
    INDEX
    Explanations

    solving equations for variables

    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
    TO
    -0.08
    AGO
    -0.08
    ago
    -0.08
    inox
    -0.07
    ogan
    -0.07
    atty
    -0.07
    erot
    -0.07
    Co
    -0.07
    pak
    -0.07
    IQ
    -0.07
    POSITIVE LOGITS
    roe
    0.11
    ugi
    0.10
    /reg
    0.10
    ased
    0.10
    ceive
    0.10
    iti
    0.10
     predecess
    0.10
    ullets
    0.09
     bitterness
    0.09
    ordinate
    0.09
    Activations Density 0.140%

    No Known Activations