© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    related to cause or origin

    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
    rippling
    -0.11
    addock
    -0.10
    .Boolean
    -0.10
    uan
    -0.10
    ');↵↵↵↵
    -0.10
    otime
    -0.10
    AWN
    -0.10
     Cotton
    -0.09
    undra
    -0.09
    iji
    -0.09
    POSITIVE LOGITS
     thanks
    0.12
     due
    0.11
    due
    0.10
     because
    0.09
     via
    0.09
     Via
    0.08
     indem
    0.08
     based
    0.08
    thanks
    0.08
     owing
    0.08
    Activations Density 0.410%

    No Known Activations