© 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. 26532
    Prev
    Next
    INDEX
    Explanations

    punishment, cane, timeouts, executed, guillotine

    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
     brutality
    -0.09
     cruelty
    -0.09
     torture
    -0.09
     fatt
    -0.09
     semen
    -0.08
     Trainer
    -0.08
     oppression
    -0.08
     Training
    -0.08
    Instr
    -0.08
     assass
    -0.08
    POSITIVE LOGITS
     public
    0.12
     privately
    0.11
     Zuk
    0.11
     Janet
    0.11
     Aurora
    0.11
     Burnett
    0.10
     adults
    0.10
     bü
    0.10
     adult
    0.10
     juven
    0.10
    Activations Density 0.034%

    No Known Activations