© 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. 58084
    Prev
    Next
    INDEX
    Explanations

    weapons and combat machinery

    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
    atos
    -0.11
    ิà¸Ļ
    -0.09
     programmed
    -0.09
     coolant
    -0.09
     Carson
    -0.09
    patch
    -0.08
    alah
    -0.08
     clipped
    -0.08
    rust
    -0.08
     fotograf
    -0.08
    POSITIVE LOGITS
    ube
    0.09
     Bridges
    0.08
     Relief
    0.08
     formul
    0.08
    labs
    0.08
     supervision
    0.08
     dom
    0.08
    stone
    0.08
     proof
    0.08
     Cle
    0.08
    Activations Density 0.007%

    No Known Activations