© 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. 61443
    Prev
    Next
    INDEX
    Explanations

    DRAM

    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
    cox
    -0.10
    croft
    -0.09
     Pew
    -0.09
    FA
    -0.09
    auce
    -0.09
    olean
    -0.08
    PATH
    -0.08
     Latter
    -0.08
     POLIT
    -0.08
    hog
    -0.08
    POSITIVE LOGITS
    rell
    0.11
    /feed
    0.08
    igi
    0.08
    sembl
    0.08
    uhl
    0.08
     Fletcher
    0.08
     Slam
    0.08
     SQUARE
    0.08
     raised
    0.08
    AGER
    0.08
    Activations Density 0.008%

    No Known Activations