© 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. 55607
    Prev
    Next
    INDEX
    Explanations

    umbrellas, chairs, and tables

    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
    bench
    -0.12
     ^(
    -0.10
     imper
    -0.10
    elts
    -0.10
     manufact
    -0.10
    ertz
    -0.10
     Embedded
    -0.10
     succes
    -0.10
     Suite
    -0.09
    ?")↵
    -0.09
    POSITIVE LOGITS
    usu
    0.09
     nic
    0.08
     enjoyable
    0.07
    /person
    0.07
     persons
    0.07
     Pon
    0.07
     Sty
    0.07
     commuting
    0.07
     easily
    0.07
     sad
    0.07
    Activations Density 0.185%

    No Known Activations