© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    eliminate threats

    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
    Forbidden
    -0.09
     shrink
    -0.09
     gradu
    -0.09
     eclipse
    -0.08
    ami
    -0.08
     eclips
    -0.08
    coop
    -0.08
     Floyd
    -0.08
     Winn
    -0.08
     stranger
    -0.08
    POSITIVE LOGITS
     elimination
    0.22
     Elim
    0.22
     threat
    0.21
     eliminate
    0.21
     eliminated
    0.21
     pes
    0.21
     threats
    0.20
     eliminating
    0.20
     elim
    0.20
    Elim
    0.20
    Activations Density 0.337%

    No Known Activations