© 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. 90325
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Hawth
    -0.10
     ratt
    -0.09
     rack
    -0.08
     suspension
    -0.08
     alike
    -0.08
    constitutional
    -0.08
    hof
    -0.08
     manifest
    -0.08
     recipro
    -0.08
     Wen
    -0.08
    POSITIVE LOGITS
     rounded
    0.11
    Unchecked
    0.10
     preferably
    0.10
     Trout
    0.10
    __()
    0.09
    edu
    0.09
    goog
    0.09
     Jak
    0.09
    _stub
    0.09
    umo
    0.09
    Activations Density 0.000%

    No Known Activations