© 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. 5543
    Prev
    Next
    INDEX
    Explanations

    conditional actions

    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
     now
    -0.19
    now
    -0.17
    Now
    -0.13
    _now
    -0.13
     Now
    -0.13
     NOW
    -0.13
    	now
    -0.11
    -now
    -0.10
    .now
    -0.10
    (now
    -0.10
    POSITIVE LOGITS
     THEN
    0.13
     gladly
    0.12
     Lud
    0.12
     afterwards
    0.11
     reconsider
    0.10
     magically
    0.10
    /ca
    0.10
     thereafter
    0.10
     Deb
    0.10
     afterward
    0.10
    Activations Density 0.040%

    No Known Activations