© 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. 2420
    Prev
    Next
    INDEX
    Explanations

    new ideas and proposals

    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
     famously
    -0.13
     notoriously
    -0.11
     notorious
    -0.09
     tricky
    -0.09
     Known
    -0.09
     commonly
    -0.09
     famous
    -0.09
    ena
    -0.09
     usually
    -0.08
     beloved
    -0.08
    POSITIVE LOGITS
    âĦ¢
    0.11
     patent
    0.10
     novel
    0.10
     proposal
    0.09
    TM
    0.09
    vio
    0.09
     Proposal
    0.09
    Disclosure
    0.09
     opener
    0.09
    (TM
    0.09
    Activations Density 0.464%

    No Known Activations