© 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. 16789
    Prev
    Next
    INDEX
    Explanations

    lord followed by names or titles

    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
    heel
    -0.09
    -0.08
    thon
    -0.08
     Zack
    -0.08
    uthor
    -0.07
    atics
    -0.07
    forth
    -0.07
     kicking
    -0.07
    ampus
    -0.07
    olu
    -0.06
    POSITIVE LOGITS
    ship
    0.18
    ships
    0.17
    lings
    0.14
     Almighty
    0.14
     Voldemort
    0.14
    liness
    0.14
    osis
    0.13
    genome
    0.13
    aby
    0.13
    kip
    0.13
    Activations Density 0.019%

    No Known Activations