© 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. 54595
    Prev
    Next
    INDEX
    Explanations

    suggest antifriction devices

    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
    :↵
    -0.10
    ï¼ļ↵
    -0.09
    Âł
    -0.09
     Âł Âł
    -0.08
    Âł↵
    -0.08
    *↵↵
    -0.08
     :↵
    -0.08
    arranty
    -0.07
     Dix
    -0.07
    ³³³³
    -0.07
    POSITIVE LOGITS
     quot
    0.10
    (predicate
    0.09
    otti
    0.09
    	matrix
    0.09
    eec
    0.09
     hin
    0.09
    hin
    0.08
     dependencies
    0.08
    ;.
    0.08
    .Raw
    0.08
    Activations Density 0.511%

    No Known Activations