© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    solve for a variable ending in a period

    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
    ILT
    -0.10
     geld
    -0.09
    ieten
    -0.09
     Nguyen
    -0.09
    ze
    -0.09
     Torres
    -0.08
     Humb
    -0.08
    ODO
    -0.08
    -en
    -0.08
    ew
    -0.08
    POSITIVE LOGITS
     totaled
    0.08
     <=>
    0.08
     Slee
    0.07
     Appalach
    0.07
     fancy
    0.07
     kinds
    0.07
    ĵĺ
    0.07
     fat
    0.07
    azen
    0.07
     decomposition
    0.07
    Activations Density 0.006%

    No Known Activations