© 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. 57622
    Prev
    Next
    INDEX
    Explanations

    error messages

    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
    kr
    -0.10
    ahead
    -0.10
     bare
    -0.09
    erc
    -0.09
    andr
    -0.09
    rar
    -0.09
    etch
    -0.09
     impl
    -0.09
    lake
    -0.09
    chers
    -0.09
    POSITIVE LOGITS
    .ravel
    0.08
     Coc
    0.08
    cot
    0.08
     sus
    0.08
    halt
    0.07
     disappointed
    0.07
    ango
    0.07
    éĢĢåĩº
    0.07
     exit
    0.07
    oker
    0.07
    Activations Density 0.007%

    No Known Activations