© 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. 4635
    Prev
    Next
    INDEX
    Explanations

    entity names or identifiers

    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
    idy
    -0.09
     âĦĸ
    -0.08
    lep
    -0.08
    FN
    -0.08
    ître
    -0.07
    ipa
    -0.07
     Wyatt
    -0.07
    vert
    -0.07
    athers
    -0.07
    riger
    -0.07
    POSITIVE LOGITS
    its
    0.10
    AAD
    0.09
     annex
    0.09
     Jord
    0.08
     Wing
    0.08
    /@
    0.08
    ically
    0.08
    otel
    0.08
     Scratch
    0.08
     dei
    0.08
    Activations Density 1.100%

    No Known Activations