© 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. 115600
    Prev
    Next
    INDEX
    Explanations

    punishment, penalty, discipline, sentencing, sanctions

    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
     cultivated
    -0.08
     forcibly
    -0.07
     destruct
    -0.07
    itr
    -0.07
     abandon
    -0.07
     devote
    -0.07
     Bene
    -0.07
     Moh
    -0.07
     contra
    -0.07
     Sund
    -0.07
    POSITIVE LOGITS
     imposed
    0.23
     inflicted
    0.21
     administered
    0.18
     inflict
    0.16
     punishments
    0.16
     imposition
    0.16
     severity
    0.16
     impose
    0.14
     devised
    0.14
     administer
    0.14
    Activations Density 0.055%

    No Known Activations