© 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. 28638
    Prev
    Next
    INDEX
    Explanations

    funny, pain, or acute

    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
     peel
    -0.11
     Beauty
    -0.10
     ugl
    -0.10
     mourn
    -0.10
     chances
    -0.09
    dee
    -0.09
     odds
    -0.09
    zer
    -0.09
    ildo
    -0.09
     longtime
    -0.09
    POSITIVE LOGITS
     surprisingly
    0.16
     addictive
    0.16
     addict
    0.13
     fun
    0.13
     unexpectedly
    0.12
     easier
    0.11
    UIS
    0.10
     remarkably
    0.10
     definit
    0.10
     underrated
    0.10
    Activations Density 0.038%

    No Known Activations