© 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. 57538
    Prev
    Next
    INDEX
    Explanations

    '80' followed by 'x'

    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
     Fore
    -0.10
     Nug
    -0.10
     Batt
    -0.10
    older
    -0.10
    notes
    -0.09
    omer
    -0.09
     SON
    -0.09
    omes
    -0.09
     impe
    -0.09
    GL
    -0.09
    POSITIVE LOGITS
    ehen
    0.07
    eu
    0.07
     Roy
    0.07
    isman
    0.07
    kus
    0.07
     loose
    0.07
    ><!--
    0.07
    aining
    0.07
     Arbitrary
    0.06
    hof
    0.06
    Activations Density 0.003%

    No Known Activations