© 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. 27527
    Prev
    Next
    INDEX
    Explanations

    "It" followed by verbs like is/was/may

    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
     Dort
    -0.09
    291
    -0.09
     stil
    -0.09
    alla
    -0.09
     nood
    -0.09
    bage
    -0.09
    wb
    -0.09
    /docs
    -0.09
    ZA
    -0.09
     Hari
    -0.09
    POSITIVE LOGITS
    spm
    0.09
    Bid
    0.09
     cater
    0.09
     originated
    0.08
     counterpart
    0.08
     Bid
    0.08
     operated
    0.08
     also
    0.08
    kos
    0.08
    also
    0.08
    Activations Density 0.711%

    No Known Activations