© 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. 15622
    Prev
    Next
    INDEX
    Explanations

    puppet and puppetry

    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
     heats
    -0.10
     raid
    -0.09
    isd
    -0.09
     doorstep
    -0.09
     institutional
    -0.09
     wild
    -0.09
    Verb
    -0.09
    .neg
    -0.09
    perse
    -0.09
     waterfall
    -0.09
    POSITIVE LOGITS
     puppet
    0.57
     Puppet
    0.47
     pup
    0.41
     strings
    0.25
    uppet
    0.25
     manipulated
    0.24
     manipulation
    0.23
     controlling
    0.22
     manipulate
    0.22
     manipulating
    0.21
    Activations Density 0.128%

    No Known Activations