© 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. 5593
    Prev
    Next
    INDEX
    Explanations

    at stake or hinges upon

    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
    cop
    -0.10
    iers
    -0.10
    ovo
    -0.09
     Kills
    -0.09
    VP
    -0.09
     Lore
    -0.09
    avar
    -0.09
     cop
    -0.09
     Destination
    -0.09
    neau
    -0.09
    POSITIVE LOGITS
     stake
    0.31
     stakes
    0.29
     hangs
    0.25
     hang
    0.22
     hinges
    0.22
     Stake
    0.22
     hanging
    0.22
     depended
    0.22
     depends
    0.21
     hinge
    0.21
    Activations Density 0.209%

    No Known Activations