© 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. 26942
    Prev
    Next
    INDEX
    Explanations

    describe lives

    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
     tide
    -0.10
    elly
    -0.09
     benches
    -0.09
    aru
    -0.09
     sift
    -0.09
     trick
    -0.09
     junction
    -0.08
     Permanent
    -0.08
    ikt
    -0.08
     slick
    -0.08
    POSITIVE LOGITS
     lives
    0.45
     life
    0.34
     Lives
    0.33
     lifestyles
    0.29
     lifestyle
    0.27
     existence
    0.25
    life
    0.24
     vida
    0.22
     Life
    0.22
    _life
    0.21
    Activations Density 0.116%

    No Known Activations