© 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. 57266
    Prev
    Next
    INDEX
    Explanations

    syntax elements

    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
    umb
    -0.09
     Zig
    -0.08
     thwart
    -0.08
     HARD
    -0.07
     pee
    -0.07
    chio
    -0.07
     Associates
    -0.07
     Sloan
    -0.07
    ane
    -0.07
     hab
    -0.07
    POSITIVE LOGITS
     manipulation
    0.10
     Manip
    0.09
     manip
    0.09
     Push
    0.09
     Broadcasting
    0.09
    fx
    0.09
    pus
    0.09
     manipulate
    0.08
    anzi
    0.08
     fx
    0.08
    Activations Density 0.020%

    No Known Activations