© 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. 18201
    Prev
    Next
    INDEX
    Explanations

    continuously happening and updating

    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
     occasional
    -0.16
    ury
    -0.12
     constant
    -0.12
     continuous
    -0.11
     never
    -0.11
     endless
    -0.10
     decidedly
    -0.10
     cupid
    -0.10
     suddenly
    -0.10
     few
    -0.10
    POSITIVE LOGITS
     reminded
    0.14
     remind
    0.13
     throughout
    0.13
     reminds
    0.12
     monitor
    0.12
     amazed
    0.11
     reminding
    0.11
     underestimate
    0.11
     abused
    0.10
     monitors
    0.10
    Activations Density 0.048%

    No Known Activations