© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    function argument followed by exponentiation

    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
    fdf
    -0.09
     Farrell
    -0.09
    PTS
    -0.09
    "↵↵↵↵
    -0.09
    fef
    -0.09
     dopo
    -0.09
    itech
    -0.09
     MOM
    -0.09
    zen
    -0.08
    reach
    -0.08
    POSITIVE LOGITS
    stin
    0.09
     pul
    0.07
    qus
    0.07
     intermediate
    0.07
     fals
    0.07
    ocious
    0.07
    kn
    0.07
     Huck
    0.07
    Intermediate
    0.07
     Intermediate
    0.07
    Activations Density 0.024%

    No Known Activations