© 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. 92479
    Prev
    Next
    INDEX
    Explanations

    chatting with

    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
    ately
    -0.12
    aval
    -0.12
    shed
    -0.11
    hon
    -0.11
    scape
    -0.11
    lessly
    -0.11
    acy
    -0.11
    lessness
    -0.11
    overs
    -0.11
     Exped
    -0.11
    POSITIVE LOGITS
     about
    0.13
    anooga
    0.12
    About
    0.09
     About
    0.09
    roulette
    0.09
    ting
    0.09
     happily
    0.09
     online
    0.08
     ami
    0.08
     despre
    0.08
    Activations Density 0.009%

    No Known Activations