© 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. 58293
    Prev
    Next
    INDEX
    Explanations

    tube with cap or loop

    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
     remnants
    -0.09
    uti
    -0.09
     signals
    -0.08
     dangers
    -0.08
     visible
    -0.08
    ulo
    -0.08
     INDIRECT
    -0.08
    è²
    -0.08
     FAR
    -0.08
     preparation
    -0.08
    POSITIVE LOGITS
     Beds
    0.09
    oment
    0.09
    gee
    0.08
     wherein
    0.08
    erts
    0.08
     Norman
    0.08
    /question
    0.07
    Ether
    0.07
     Crest
    0.07
    ational
    0.07
    Activations Density 0.091%

    No Known Activations