© 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. 4021
    Prev
    Next
    INDEX
    Explanations

    determines what follows

    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
     only
    -0.09
    uma
    -0.09
     material
    -0.09
    idas
    -0.08
    inged
    -0.08
    ior
    -0.08
    并
    -0.08
    iad
    -0.08
    %(
    -0.08
     Bav
    -0.08
    POSITIVE LOGITS
    irs
    0.10
     truly
    0.10
     determines
    0.09
     Decide
    0.09
    atan
    0.09
     matters
    0.09
    adding
    0.09
    irl
    0.09
     decide
    0.08
    vie
    0.08
    Activations Density 0.135%

    No Known Activations