© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58725
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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
    Negative Logits
    hear
    -0.12
    -spe
    -0.11
     Charl
    -0.10
    jar
    -0.10
    pc
    -0.10
    cour
    -0.09
     Sweep
    -0.09
    NBC
    -0.09
    /detail
    -0.09
     Alexand
    -0.09
    POSITIVE LOGITS
     Suff
    0.09
     Citadel
    0.07
    craft
    0.07
    hee
    0.07
    /></
    0.07
    aye
    0.07
     <:
    0.06
    butt
    0.06
    ocup
    0.06
     lul
    0.06
    Activations Density 0.004%

    No Known Activations