© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56664
    Prev
    Next
    INDEX
    Explanations

    expiration dates and times

    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
    oret
    -0.08
     sans
    -0.08
     fork
    -0.07
    -and
    -0.07
    /IP
    -0.07
    oni
    -0.07
    orig
    -0.07
    Ä
    -0.07
     constructive
    -0.07
     recorder
    -0.07
    POSITIVE LOGITS
    ald
    0.10
    ção
    0.10
     Valentine
    0.10
    anto
    0.10
    .tm
    0.09
    krit
    0.09
     Flesh
    0.09
     Coral
    0.09
    quan
    0.09
     policym
    0.09
    Activations Density 0.003%

    No Known Activations