© 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. 57066
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     Hicks
    -0.08
    edImage
    -0.08
    ville
    -0.08
    ette
    -0.08
     tern
    -0.08
     Champ
    -0.08
     Uri
    -0.08
    она
    -0.08
     vigil
    -0.07
     Devin
    -0.07
    POSITIVE LOGITS
    ibbean
    0.08
    ream
    0.08
     corres
    0.08
    /testing
    0.08
    finity
    0.08
    pag
    0.08
    xima
    0.08
    LOSS
    0.08
    lify
    0.08
    .must
    0.08
    Activations Density 0.117%

    No Known Activations