© 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. 58170
    Prev
    Next
    INDEX
    Explanations

    FPGA, Xilinx, ASIC

    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
    quan
    -0.08
     Egg
    -0.08
    /calendar
    -0.08
     imitation
    -0.08
    inst
    -0.08
     East
    -0.07
     Din
    -0.07
    spd
    -0.07
    IMIT
    -0.07
    lever
    -0.07
    POSITIVE LOGITS
    och
    0.12
     mega
    0.09
     Alter
    0.09
    mega
    0.09
     FPGA
    0.09
    tail
    0.09
     ende
    0.08
     OT
    0.08
     mortar
    0.08
     satur
    0.08
    Activations Density 0.014%

    No Known Activations