© 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. 54099
    Prev
    Next
    INDEX
    Explanations

    divided 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
    pus
    -0.09
     favoured
    -0.09
    ambre
    -0.09
    neys
    -0.08
    coli
    -0.08
     Maggie
    -0.08
     telefon
    -0.08
    agate
    -0.08
    opsis
    -0.08
    itional
    -0.08
    POSITIVE LOGITS
    PRO
    0.08
     Tape
    0.08
     paid
    0.08
     connecting
    0.08
     present
    0.07
     presente
    0.07
     Pap
    0.07
    yan
    0.07
    les
    0.07
     menstr
    0.07
    Activations Density 0.003%

    No Known Activations