© 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. 50609
    Prev
    Next
    INDEX
    Explanations

    suicide attempts, discharged patients

    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
     nep
    -0.10
     reorder
    -0.09
     dames
    -0.09
     tack
    -0.09
     reim
    -0.09
    ICC
    -0.08
     FEC
    -0.08
     Retro
    -0.08
    phia
    -0.08
     repar
    -0.08
    POSITIVE LOGITS
     suicide
    0.69
     suicidal
    0.61
     Suicide
    0.61
     suicides
    0.54
     suic
    0.51
    Su
    0.38
    -su
    0.37
    su
    0.37
     Su
    0.33
    _su
    0.33
    Activations Density 0.415%

    No Known Activations