© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115810
    Prev
    Next
    INDEX
    Explanations

    shutting down or closing

    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
     uncon
    -0.10
     Wa
    -0.08
     forgotten
    -0.08
     Forgot
    -0.08
     tiny
    -0.07
     ordinarily
    -0.07
    forgot
    -0.07
     skipped
    -0.07
     tall
    -0.07
    Mismatch
    -0.07
    POSITIVE LOGITS
     shutdown
    0.27
     shutting
    0.25
     shut
    0.24
     closure
    0.24
     demise
    0.23
     banning
    0.22
     ban
    0.21
     Shutdown
    0.21
     closing
    0.20
     Shut
    0.20
    Activations Density 0.121%

    No Known Activations