© 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. 55210
    Prev
    Next
    INDEX
    Explanations

    court filings, code, or data

    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
    nf
    -0.09
    burger
    -0.09
    mark
    -0.09
    nr
    -0.08
    sa
    -0.08
    jaw
    -0.08
    !↵↵↵↵↵↵
    -0.08
    been
    -0.08
    \Id
    -0.08
     elÅij
    -0.08
    POSITIVE LOGITS
     Ross
    0.09
    ongs
    0.08
     ICE
    0.08
     SAND
    0.08
     sist
    0.08
     Wolff
    0.08
     salt
    0.08
     surviving
    0.07
    ICE
    0.07
     Doch
    0.07
    Activations Density 0.004%

    No Known Activations