© 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. 640
    Prev
    Next
    INDEX
    Explanations

    places or locations

    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
     indoors
    -0.12
     onstage
    -0.12
     downtown
    -0.11
    [:]
    -0.11
     Downtown
    -0.10
    fully
    -0.10
    .springboot
    -0.10
    ICI
    -0.10
    tur
    -0.09
     Sto
    -0.09
    POSITIVE LOGITS
    /on
    0.13
     where
    0.12
    ìĹIJìĦľ
    0.10
     environment
    0.09
     où
    0.09
     sidebar
    0.08
    -wide
    0.08
    /mobile
    0.08
    ìĹIJ
    0.08
    abouts
    0.08
    Activations Density 3.048%

    No Known Activations