© 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. 47781
    Prev
    Next
    INDEX
    Explanations

    forcing or compelled action

    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
     lap
    -0.08
     soc
    -0.08
    hait
    -0.08
    ADI
    -0.08
     sinc
    -0.08
    uml
    -0.08
     cruz
    -0.08
    314
    -0.08
    anse
    -0.08
     chained
    -0.08
    POSITIVE LOGITS
    ably
    0.14
    /man
    0.13
     unwilling
    0.13
    -feed
    0.12
     resisted
    0.12
    (force
    0.12
     Til
    0.12
    feed
    0.11
     resisting
    0.11
     reluctant
    0.11
    Activations Density 0.012%

    No Known Activations