© 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. 114629
    Prev
    Next
    INDEX
    Explanations

    commands and prohibitions

    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
     shouldn
    -0.10
    sr
    -0.09
    ados
    -0.09
     bothering
    -0.09
     anywhere
    -0.09
     Bew
    -0.08
    noop
    -0.08
     disreg
    -0.08
    icks
    -0.08
    pes
    -0.08
    POSITIVE LOGITS
     me
    0.16
     irreversible
    0.11
     suspended
    0.10
    onna
    0.09
    oran
    0.09
     Bordeaux
    0.09
    æĪij
    0.09
    /chat
    0.09
     mee
    0.09
    upd
    0.09
    Activations Density 0.031%

    No Known Activations