© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    racing Grand Prix

    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
    inkel
    -0.08
     marching
    -0.07
     crow
    -0.06
     Gors
    -0.06
     tail
    -0.06
    ayar
    -0.06
     struck
    -0.06
     Bio
    -0.06
     hiking
    -0.06
    dre
    -0.06
    POSITIVE LOGITS
    nak
    0.13
     racing
    0.12
    uns
    0.11
     Racing
    0.11
     race
    0.11
     Race
    0.11
     fragmented
    0.11
    anford
    0.10
     airs
    0.10
    wen
    0.10
    Activations Density 0.170%

    No Known Activations