© 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. 27296
    Prev
    Next
    INDEX
    Explanations

    addiction and withdrawal

    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
     dinner
    -0.10
    /render
    -0.10
     beaut
    -0.10
    uste
    -0.10
     Clipboard
    -0.10
     Emanuel
    -0.09
     erosion
    -0.09
     bowling
    -0.09
     [+
    -0.09
     Invitation
    -0.09
    POSITIVE LOGITS
     addiction
    0.40
     addicted
    0.38
     addicts
    0.37
     withdrawal
    0.36
     addict
    0.36
     addictive
    0.34
     Addiction
    0.32
     withdrawals
    0.31
     Withdraw
    0.30
     craving
    0.29
    Activations Density 0.158%

    No Known Activations