© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117435
    Prev
    Next
    INDEX
    Explanations

    turn into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Guild
    -0.10
    ught
    -0.10
    idon
    -0.10
     increment
    -0.10
    rug
    -0.10
     clipped
    -0.10
    cket
    -0.09
     Shr
    -0.09
     tw
    -0.09
    /release
    -0.09
    POSITIVE LOGITS
     around
    0.10
     glance
    0.09
    mare
    0.09
     transl
    0.09
     pale
    0.09
    ä¸Ģ页
    0.09
     sola
    0.09
     vra
    0.09
    utto
    0.08
    -over
    0.08
    Activations Density 0.008%

    No Known Activations