© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    lost art, derogatory term, inconsistent punishment, produces library, destination, disperse funds, spotlight, episodes of violence, packaging, retrieve

    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
    dit
    -0.08
    heim
    -0.08
    aud
    -0.08
    lessly
    -0.08
     Vaughan
    -0.07
     abort
    -0.07
     enthus
    -0.07
     carriers
    -0.07
     Caul
    -0.07
    Aud
    -0.07
    POSITIVE LOGITS
     Proud
    0.09
    -Ta
    0.08
    stro
    0.08
    /mark
    0.08
     Nagar
    0.08
    "'
    0.08
    pike
    0.08
    "w
    0.08
     transpose
    0.08
     Laden
    0.08
    Activations Density 0.435%

    No Known Activations