© 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. 2411
    Prev
    Next
    INDEX
    Explanations

    buttons, lengths, Island, triangles

    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
     Sher
    -0.09
    legg
    -0.09
    inidad
    -0.08
     spel
    -0.08
    seau
    -0.08
    Sher
    -0.08
    aes
    -0.08
     Burton
    -0.08
     Built
    -0.08
    APA
    -0.08
    POSITIVE LOGITS
    Ùī
    0.09
     Maid
    0.08
    Arg
    0.08
    /work
    0.08
    automation
    0.07
     Gerry
    0.07
     bump
    0.07
    asley
    0.07
    tdown
    0.07
     Maz
    0.07
    Activations Density 1.343%

    No Known Activations