© 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. 27642
    Prev
    Next
    INDEX
    Explanations

    punishment, punjab, punter

    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
    ably
    -0.09
     Wolff
    -0.08
    es
    -0.08
    ingly
    -0.08
    eer
    -0.08
    eses
    -0.08
     Advisors
    -0.08
    eus
    -0.07
    iros
    -0.07
     illegally
    -0.07
    POSITIVE LOGITS
     Pun
    0.17
     punishment
    0.16
     punishing
    0.15
     punishments
    0.14
    pun
    0.14
     punish
    0.14
     unintended
    0.13
     pun
    0.13
     punished
    0.13
    ishment
    0.13
    Activations Density 0.003%

    No Known Activations