© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56388
    Prev
    Next
    INDEX
    Explanations

    guard command or rail

    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
    cks
    -0.11
    TED
    -0.08
    exo
    -0.08
     Symphony
    -0.08
    borah
    -0.08
    anal
    -0.08
    ocs
    -0.08
    oui
    -0.08
    orges
    -0.08
    ef
    -0.08
    POSITIVE LOGITS
    er
    0.15
    edly
    0.15
    ships
    0.12
    rails
    0.11
    ìĹ´
    0.11
    rail
    0.10
    etten
    0.10
    ians
    0.10
    iola
    0.09
    erb
    0.09
    Activations Density 0.006%

    No Known Activations