© 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. 7138
    Prev
    Next
    INDEX
    Explanations

    wreak havoc

    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
    YOU
    -0.10
     chasing
    -0.10
     Hib
    -0.10
     oltre
    -0.10
     grues
    -0.10
     propensity
    -0.10
    printStats
    -0.10
     chase
    -0.10
     Protector
    -0.10
     Dak
    -0.09
    POSITIVE LOGITS
     havoc
    0.38
     magic
    0.27
     wonders
    0.25
     miracles
    0.21
    magic
    0.19
     MAGIC
    0.18
     wreak
    0.18
     Magic
    0.17
     miracle
    0.17
     spells
    0.16
    Activations Density 0.027%

    No Known Activations