© 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. 91740
    Prev
    Next
    INDEX
    Explanations

    adverse effects after poisoning

    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
     traumat
    -0.13
    dar
    -0.10
    anders
    -0.10
    Broken
    -0.10
     tra
    -0.10
     Spect
    -0.10
     Stress
    -0.09
     gou
    -0.09
     scars
    -0.09
    izen
    -0.09
    POSITIVE LOGITS
     effects
    0.24
     Effects
    0.21
     symptoms
    0.20
    Effects
    0.19
    effects
    0.18
     Symptoms
    0.18
     incapac
    0.17
     poisoned
    0.17
     antid
    0.16
     halluc
    0.16
    Activations Density 0.075%

    No Known Activations