© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    `../` or similar relative path components

    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
    ",-
    -0.11
    dee
    -0.10
    dea
    -0.10
    \a
    -0.10
    "",
    -0.10
    -den
    -0.10
    idth
    -0.10
    adc
    -0.10
    ibble
    -0.10
    /socket
    -0.10
    POSITIVE LOGITS
    ums
    0.06
     --
    0.06
     scre
    0.06
    itous
    0.06
     moto
    0.06
    /IP
    0.06
     interes
    0.05
     Phen
    0.05
    ...
    0.05
    nis
    0.05
    Activations Density 0.095%

    No Known Activations