© 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. 3360
    Prev
    Next
    INDEX
    Explanations

    building and finishing things

    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
    streams
    -0.09
    ubar
    -0.09
     stead
    -0.09
     pragma
    -0.08
     Rede
    -0.08
     ticker
    -0.08
     rég
    -0.08
     mim
    -0.08
    lei
    -0.08
     ment
    -0.08
    POSITIVE LOGITS
     finished
    0.16
     Finished
    0.15
     pre
    0.14
     assembly
    0.14
     assembling
    0.14
     manufacturing
    0.14
     completed
    0.14
     manufacture
    0.13
     assemble
    0.13
     finalized
    0.13
    Activations Density 0.349%

    No Known Activations