© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    culture or cultural

    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
    ÃĦ
    -0.10
    .gg
    -0.10
     Admission
    -0.10
     Sisters
    -0.09
    uen
    -0.09
    orial
    -0.09
    ccc
    -0.09
    ners
    -0.09
    ERO
    -0.09
     Otto
    -0.09
    POSITIVE LOGITS
    lle
    0.11
    urally
    0.09
     shock
    0.09
    tu
    0.08
     heritage
    0.08
     scre
    0.08
     Moor
    0.08
    pos
    0.08
     Shock
    0.08
    pon
    0.08
    Activations Density 0.223%

    No Known Activations