© 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. 54327
    Prev
    Next
    INDEX
    Explanations

    code loops

    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
     anonymous
    -0.07
    oms
    -0.07
    fbe
    -0.07
    tep
    -0.07
    .Inject
    -0.07
     Insider
    -0.07
     aur
    -0.07
     multim
    -0.07
    gid
    -0.06
    uxe
    -0.06
    POSITIVE LOGITS
     Manufacturer
    0.11
    strand
    0.10
    jem
    0.10
    ell
    0.10
     drowned
    0.10
    оÑı
    0.09
    .sourceforge
    0.09
    tribution
    0.09
    opal
    0.09
     attributable
    0.09
    Activations Density 0.017%

    No Known Activations