© 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. 113884
    Prev
    Next
    INDEX
    Explanations

    click to lock or secure

    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
     Coco
    -0.11
    PAD
    -0.10
    PPP
    -0.10
     redes
    -0.10
     sling
    -0.10
    webs
    -0.09
     sacks
    -0.09
    nek
    -0.09
     spar
    -0.09
     Silk
    -0.09
    POSITIVE LOGITS
     securely
    0.16
     latch
    0.15
     locked
    0.14
     snaps
    0.14
     tight
    0.13
     tightly
    0.13
     firmly
    0.13
     tightened
    0.13
     secure
    0.13
     snug
    0.12
    Activations Density 0.533%

    No Known Activations