© 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. 3248
    Prev
    Next
    INDEX
    Explanations

    designing and manufacturing

    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
     instantly
    -0.07
     initiation
    -0.07
     Tre
    -0.07
     quickly
    -0.06
     narr
    -0.06
     Quickly
    -0.06
     resident
    -0.06
     Rin
    -0.06
    tra
    -0.06
     unofficial
    -0.06
    POSITIVE LOGITS
     design
    0.21
     designing
    0.20
     designs
    0.18
     designers
    0.17
     Design
    0.16
    /design
    0.16
    Design
    0.15
    design
    0.15
    设计
    0.15
     Designs
    0.15
    Activations Density 0.613%

    No Known Activations