© 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. 4430
    Prev
    Next
    INDEX
    Explanations

    java.util classes

    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
    egen
    -0.10
     Verg
    -0.09
    cul
    -0.09
     Wax
    -0.08
    -num
    -0.08
    fall
    -0.08
    aje
    -0.08
    wall
    -0.08
    uga
    -0.08
    acias
    -0.08
    POSITIVE LOGITS
    .jar
    0.16
    .zip
    0.15
    .function
    0.12
    .Event
    0.12
    .regex
    0.12
    .concurrent
    0.12
    .ArrayList
    0.12
    .Dictionary
    0.11
    .logging
    0.10
    .Bit
    0.10
    Activations Density 0.007%

    No Known Activations