© 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. 27235
    Prev
    Next
    INDEX
    Explanations

    forever, positively, life, living, industries

    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
    cron
    -0.10
     Cro
    -0.09
    iseconds
    -0.09
    ades
    -0.09
     Cron
    -0.09
     ob
    -0.09
     Af
    -0.09
     unusual
    -0.09
     oblivious
    -0.09
     cron
    -0.09
    POSITIVE LOGITS
     positively
    0.20
     positive
    0.17
     Positive
    0.15
     negatively
    0.14
    posit
    0.14
     forever
    0.14
    positive
    0.14
    Positive
    0.14
     Forever
    0.13
     profoundly
    0.13
    Activations Density 0.147%

    No Known Activations