© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14676
    Prev
    Next
    INDEX
    Explanations

    relaxation and formal proceedings

    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
     cro
    -0.10
    :void
    -0.10
    rica
    -0.10
    ĺ
    -0.10
    ucch
    -0.09
     Abed
    -0.09
    abwe
    -0.09
    care
    -0.09
    ocrin
    -0.09
     Blow
    -0.09
    POSITIVE LOGITS
    reff
    0.08
     Relax
    0.08
     Lounge
    0.08
     relaxation
    0.08
     Breaking
    0.08
    edor
    0.08
    orman
    0.08
    .dep
    0.07
     Dipl
    0.07
     relaxing
    0.07
    Activations Density 0.015%

    No Known Activations