© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    utility or function

    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
    --
    -0.09
    anya
    -0.08
     Wort
    -0.08
     wol
    -0.08
     proced
    -0.08
    "--
    -0.07
    aph
    -0.07
     sacrific
    -0.07
    ansion
    -0.07
     *
    -0.07
    POSITIVE LOGITS
    -</
    0.10
    bah
    0.09
    Âł↵
    0.09
     [âĢ¦
    0.09
    nof
    0.09
     []).
    0.08
     Aires
    0.08
    .sup
    0.08
    CLICK
    0.08
    []↵
    0.08
    Activations Density 8.483%

    No Known Activations