© 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. 2159
    Prev
    Next
    INDEX
    Explanations

    namely, viz, specifically

    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
    ring
    -0.09
    ibir
    -0.09
    lice
    -0.09
    ibur
    -0.09
    lé
    -0.09
    <Any
    -0.08
    Monkey
    -0.08
     ()=>
    -0.08
    ende
    -0.08
     emphas
    -0.08
    POSITIVE LOGITS
     namely
    0.14
     Nam
    0.13
     viz
    0.12
    nam
    0.12
     Specifically
    0.11
    Nam
    0.09
     Trou
    0.07
     ie
    0.07
     specifically
    0.07
     (#
    0.07
    Activations Density 0.563%

    No Known Activations