© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114626
    Prev
    Next
    INDEX
    Explanations

    tired of

    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
     downfall
    -0.10
     dissolution
    -0.09
     ag
    -0.09
    ny
    -0.09
    idia
    -0.09
    658
    -0.09
     Bench
    -0.08
    cha
    -0.08
     insol
    -0.08
     Devils
    -0.08
    POSITIVE LOGITS
     fed
    0.19
     tired
    0.16
     hearing
    0.15
    fed
    0.14
     sick
    0.13
     weary
    0.13
     Fed
    0.12
     being
    0.12
     Sick
    0.12
    Fed
    0.12
    Activations Density 0.011%

    No Known Activations