© 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. 57193
    Prev
    Next
    INDEX
    Explanations

    suggesting or asking questions

    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
     driv
    -0.08
    lib
    -0.08
     interactions
    -0.08
    aba
    -0.08
    agy
    -0.07
    ãĤº
    -0.07
     Ly
    -0.07
     announcing
    -0.07
    çī
    -0.07
     bas
    -0.07
    POSITIVE LOGITS
     impro
    0.11
     sights
    0.10
     calmly
    0.10
     respectfully
    0.10
    etsy
    0.09
    nect
    0.09
     gren
    0.09
     Pere
    0.09
     noticed
    0.09
    že
    0.09
    Activations Density 0.017%

    No Known Activations