© 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. 57530
    Prev
    Next
    INDEX
    Explanations

    time flying by

    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
     OE
    -0.09
     drawing
    -0.09
     peak
    -0.08
    arious
    -0.08
     drew
    -0.08
     draw
    -0.08
     environ
    -0.08
     Peak
    -0.08
     pick
    -0.08
    peer
    -0.08
    POSITIVE LOGITS
     Bund
    0.10
     bundled
    0.09
    voie
    0.09
    izr
    0.09
    chen
    0.09
     gele
    0.09
    alles
    0.08
    inch
    0.08
     bund
    0.08
    nio
    0.08
    Activations Density 0.040%

    No Known Activations