© 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. 49377
    Prev
    Next
    INDEX
    Explanations

    trapped in

    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
    icht
    -0.15
     racks
    -0.12
    Manifest
    -0.11
    Qui
    -0.11
     Cocoa
    -0.11
     Yao
    -0.11
     disin
    -0.11
     acquaint
    -0.11
     withdrawn
    -0.11
    cpt
    -0.11
    POSITIVE LOGITS
     trapped
    0.16
     trapping
    0.12
     trap
    0.11
     traps
    0.10
     Trap
    0.10
     between
    0.10
     pinned
    0.08
    between
    0.07
    Trap
    0.07
    rer
    0.07
    Activations Density 0.038%

    No Known Activations