© 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. 3419
    Prev
    Next
    INDEX
    Explanations

    actions performed by a person

    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
     receive
    -0.16
     receives
    -0.15
     Receive
    -0.15
     receiving
    -0.13
     experiences
    -0.13
     received
    -0.13
     realise
    -0.13
     Rece
    -0.12
     regret
    -0.12
     experience
    -0.12
    POSITIVE LOGITS
     provided
    0.15
     bestowed
    0.14
     inflicted
    0.14
     imposed
    0.13
     provide
    0.13
     supplied
    0.13
     impose
    0.12
     imposes
    0.12
     inflict
    0.12
     impart
    0.11
    Activations Density 0.047%

    No Known Activations