© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54916
    Prev
    Next
    INDEX
    Explanations

    Lemberg

    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
    die
    -0.09
    ght
    -0.09
    ighton
    -0.08
     tá
    -0.08
     McN
    -0.08
    fy
    -0.08
    CLAIM
    -0.08
     Ada
    -0.07
    ollo
    -0.07
    digit
    -0.07
    POSITIVE LOGITS
    haar
    0.10
     Ole
    0.09
    ati
    0.09
    addin
    0.09
    rand
    0.08
    anka
    0.08
    iland
    0.08
     overnight
    0.08
     witnessed
    0.08
    Metrics
    0.08
    Activations Density 0.050%

    No Known Activations