© 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. 57399
    Prev
    Next
    INDEX
    Explanations

    applicable descriptions

    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
    ningen
    -0.10
    FFF
    -0.10
     CONTRIBUTORS
    -0.09
    Credits
    -0.09
     THEME
    -0.09
    ownt
    -0.09
     Credits
    -0.09
    Reviews
    -0.08
    hof
    -0.08
     thereafter
    -0.08
    POSITIVE LOGITS
     please
    0.11
     entered
    0.10
    please
    0.09
     Please
    0.09
    lut
    0.09
     Describe
    0.08
     enter
    0.08
    circle
    0.08
     entering
    0.08
     certify
    0.08
    Activations Density 0.016%

    No Known Activations