© 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. 7216
    Prev
    Next
    INDEX
    Explanations

    duct or ductal contexts

    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
    izont
    -0.09
     hut
    -0.08
     Lions
    -0.08
    ENCE
    -0.08
    dea
    -0.08
     sare
    -0.08
    SSION
    -0.08
    kont
    -0.08
    sla
    -0.08
    heit
    -0.08
    POSITIVE LOGITS
     duct
    0.21
     tape
    0.13
    work
    0.12
     Tape
    0.12
    ility
    0.11
     Duck
    0.11
    tape
    0.11
    duct
    0.11
    DUCT
    0.11
     pipe
    0.10
    Activations Density 0.011%

    No Known Activations