© 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. 32329
    Prev
    Next
    INDEX
    Explanations

    avoiding negative outcomes

    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
     Bey
    -0.09
     unins
    -0.09
    chu
    -0.08
     acknowled
    -0.08
    ulla
    -0.08
     explicit
    -0.08
     severely
    -0.08
     FEC
    -0.08
     Raz
    -0.08
     budgets
    -0.08
    POSITIVE LOGITS
     surprises
    0.25
     accidentally
    0.25
     later
    0.20
     inadvertently
    0.20
     unexpectedly
    0.20
     surprise
    0.19
     accidental
    0.18
     unintention
    0.18
     accident
    0.18
     unexpected
    0.17
    Activations Density 0.128%

    No Known Activations