© 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. 91513
    Prev
    Next
    INDEX
    Explanations

    death and fatal accidents

    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
     chopping
    -0.12
     terrorist
    -0.10
     slaughter
    -0.10
     indiscrim
    -0.10
     Mild
    -0.10
    attack
    -0.09
     terminating
    -0.09
    lasses
    -0.09
     massac
    -0.09
    lass
    -0.09
    POSITIVE LOGITS
     tragic
    0.14
     trag
    0.13
     overd
    0.12
     complications
    0.12
     embarrassment
    0.11
     fatal
    0.11
     suff
    0.11
     accidentally
    0.10
     tragedy
    0.10
     electro
    0.10
    Activations Density 0.737%

    No Known Activations