© 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. 2203
    Prev
    Next
    INDEX
    Explanations

    at some point

    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
    ós
    -0.07
    amic
    -0.07
    usted
    -0.07
    erty
    -0.07
    opl
    -0.07
    lass
    -0.07
    ingen
    -0.07
     Markus
    -0.07
    zer
    -0.07
     Owen
    -0.07
    POSITIVE LOGITS
     atleast
    0.22
     somewhere
    0.19
     either
    0.19
     somew
    0.18
     SOME
    0.18
     sooner
    0.18
     SOM
    0.15
     EITHER
    0.15
     Either
    0.15
    either
    0.15
    Activations Density 0.351%

    No Known Activations