© 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. 30114
    Prev
    Next
    INDEX
    Explanations

    due to or canceled

    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
     uninterrupted
    -0.10
     deceased
    -0.10
    ocks
    -0.09
    intern
    -0.09
     kitt
    -0.09
    chte
    -0.09
     subordinate
    -0.09
     backstage
    -0.09
    lingen
    -0.09
     supervised
    -0.09
    POSITIVE LOGITS
     due
    0.30
    due
    0.27
    _due
    0.23
     because
    0.21
     Due
    0.21
     wegen
    0.19
     reasons
    0.18
    Due
    0.18
     citing
    0.18
     owing
    0.17
    Activations Density 0.645%

    No Known Activations