© 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. 54514
    Prev
    Next
    INDEX
    Explanations

    dioxin compounds

    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
    bags
    -0.09
    ly
    -0.09
    iations
    -0.09
    olson
    -0.08
    ona
    -0.08
    blog
    -0.08
     Loads
    -0.08
    bing
    -0.08
    wright
    -0.08
     slip
    -0.07
    POSITIVE LOGITS
     Hanna
    0.09
    orus
    0.09
    ÈĻi
    0.09
    ï¼ģ",
    0.08
    amma
    0.08
    chaft
    0.08
     trust
    0.08
    upa
    0.08
     cir
    0.08
    ustria
    0.08
    Activations Density 0.003%

    No Known Activations