© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    citations markers

    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
    umbo
    -0.10
    ument
    -0.09
    unn
    -0.09
    unning
    -0.09
    ahun
    -0.08
    ilst
    -0.08
     forwards
    -0.08
    artz
    -0.08
    ticks
    -0.08
     Tick
    -0.08
    POSITIVE LOGITS
     futures
    0.09
     fre
    0.08
     ($.
    0.08
    edm
    0.08
     Projection
    0.08
     symp
    0.08
     shade
    0.07
    wap
    0.07
     projection
    0.07
     Mayer
    0.07
    Activations Density 0.008%

    No Known Activations