© 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. 55833
    Prev
    Next
    INDEX
    Explanations

    decide whether, salvation of, break a, save humanity

    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
     inevitable
    -0.10
     inevitably
    -0.09
    iva
    -0.09
    ore
    -0.08
     Ñģк
    -0.08
    ches
    -0.08
     affected
    -0.08
     Peek
    -0.08
    eni
    -0.08
    olds
    -0.08
    POSITIVE LOGITS
     entire
    0.13
     Entire
    0.13
     costing
    0.10
    esson
    0.09
     literally
    0.09
    career
    0.09
     keyed
    0.09
     ance
    0.09
     whole
    0.09
    atra
    0.09
    Activations Density 0.060%

    No Known Activations