© 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. 3786
    Prev
    Next
    INDEX
    Explanations

    containing or featuring descriptive elements

    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
    oa
    -0.08
     Moss
    -0.08
    iu
    -0.07
     Wan
    -0.07
    ноп
    -0.07
    berg
    -0.07
    _Pl
    -0.07
    zilla
    -0.07
     Medium
    -0.07
    ete
    -0.07
    POSITIVE LOGITS
     containing
    0.21
     featuring
    0.15
     contains
    0.13
     Featuring
    0.13
     contain
    0.12
    cont
    0.12
     possessing
    0.12
    Containing
    0.12
     Contains
    0.11
    åIJ«
    0.11
    Activations Density 0.894%

    No Known Activations