© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56538
    Prev
    Next
    INDEX
    Explanations

    bowling and pitches

    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
     cred
    -0.09
     sce
    -0.09
     noises
    -0.09
    ians
    -0.09
     appropriated
    -0.09
    umes
    -0.09
     scratched
    -0.08
    &e
    -0.08
    bor
    -0.08
    ETS
    -0.08
    POSITIVE LOGITS
     plain
    0.09
     negot
    0.09
    /style
    0.08
    attern
    0.08
     Ir
    0.08
    ounder
    0.08
     lokal
    0.08
     Apt
    0.08
     Sham
    0.08
    alo
    0.08
    Activations Density 0.006%

    No Known Activations