© 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. 4727
    Prev
    Next
    INDEX
    Explanations

    effects on outcomes

    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
    PLUS
    -0.10
    Carthy
    -0.10
     ^↵
    -0.09
    kol
    -0.09
    iped
    -0.09
    ROL
    -0.09
    gren
    -0.09
     Plus
    -0.09
    erno
    -0.08
    apg
    -0.08
    POSITIVE LOGITS
     Tested
    0.09
    DIRECT
    0.09
    bane
    0.08
    lien
    0.08
     differently
    0.08
     independently
    0.07
     Spinner
    0.07
     directly
    0.07
    lyn
    0.07
     tested
    0.07
    Activations Density 0.415%

    No Known Activations