© 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. 46386
    Prev
    Next
    INDEX
    Explanations

    looked at or took and

    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
    rush
    -0.11
     myster
    -0.11
     apparently
    -0.11
     later
    -0.11
     unexpected
    -0.11
     unexpectedly
    -0.11
     surprising
    -0.10
     Later
    -0.10
    unexpected
    -0.10
     inexp
    -0.09
    POSITIVE LOGITS
     glanced
    0.12
     glance
    0.11
     wiping
    0.10
    Continue
    0.10
     sighed
    0.10
     ajust
    0.10
     Continue
    0.09
     reflection
    0.09
    emm
    0.09
     scratch
    0.09
    Activations Density 0.117%

    No Known Activations