© 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. 113262
    Prev
    Next
    INDEX
    Explanations

    risk and safety limits

    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
    synthesize
    -0.11
     Singer
    -0.11
     filmy
    -0.11
     synth
    -0.10
     sketch
    -0.10
     Hollow
    -0.09
     expense
    -0.09
     insurance
    -0.08
     Creature
    -0.08
     Awards
    -0.08
    POSITIVE LOGITS
     Annex
    0.15
     derog
    0.14
     ASTM
    0.14
     consumer
    0.12
     intentionally
    0.12
     pac
    0.12
     unacceptable
    0.12
     hazard
    0.12
     hazards
    0.12
    /product
    0.11
    Activations Density 3.166%

    No Known Activations