© 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. 17260
    Prev
    Next
    INDEX
    Explanations

    putting life at risk

    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
     Cas
    -0.09
    aber
    -0.08
     hookup
    -0.08
    apon
    -0.08
     desn
    -0.08
     bub
    -0.08
    KEEP
    -0.07
    547
    -0.07
    eg
    -0.07
     Bes
    -0.07
    POSITIVE LOGITS
     doing
    0.18
     committing
    0.18
     putting
    0.17
     acting
    0.17
     thereby
    0.17
     essentially
    0.16
     giving
    0.16
     risking
    0.16
     youre
    0.15
     creating
    0.15
    Activations Density 0.326%

    No Known Activations