© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    search engine related terms

    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
    amental
    -0.11
    /source
    -0.11
     sources
    -0.11
     researching
    -0.10
    sw
    -0.10
    /sources
    -0.10
    gger
    -0.09
    STM
    -0.09
    oman
    -0.09
    wy
    -0.09
    POSITIVE LOGITS
    ers
    0.11
    light
    0.11
     engine
    0.10
    -engine
    0.10
    awn
    0.09
    es
    0.09
     engines
    0.09
     Engines
    0.09
     Engine
    0.09
    lights
    0.09
    Activations Density 0.129%

    No Known Activations