© 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. 30692
    Prev
    Next
    INDEX
    Explanations

    cloning, genetically, cyborgs

    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
     Wag
    -0.11
     wag
    -0.10
     tents
    -0.10
     wagon
    -0.09
     vendor
    -0.09
     Conj
    -0.09
     fa
    -0.09
     festival
    -0.09
     trailed
    -0.09
     nested
    -0.08
    POSITIVE LOGITS
     genetically
    0.23
     clones
    0.23
     clone
    0.22
     cloned
    0.22
     cloning
    0.22
     vat
    0.20
     genetic
    0.19
     created
    0.19
     experiment
    0.19
     artificially
    0.19
    Activations Density 0.163%

    No Known Activations