© 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. 3667
    Prev
    Next
    INDEX
    Explanations

    commitment and freedom

    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
    Not in Any Lists

    No Comments

    Negative Logits
     discriminator
    -0.12
    .cgi
    -0.11
     Discrim
    -0.10
     Conc
    -0.10
     insult
    -0.10
    uve
    -0.10
     humili
    -0.10
     expos
    -0.10
     insults
    -0.10
     extortion
    -0.10
    POSITIVE LOGITS
     freedom
    0.27
     commitment
    0.22
     Freedom
    0.22
     independence
    0.21
    Freedom
    0.21
     freedoms
    0.20
     Independence
    0.19
     commitments
    0.18
     cla
    0.18
     Commit
    0.17
    Activations Density 0.054%

    No Known Activations