© 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. 90182
    Prev
    Next
    INDEX
    Explanations

    misfortune

    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
     covert
    -0.11
     Guill
    -0.10
     reinc
    -0.09
     alleg
    -0.09
     subtle
    -0.09
     secrets
    -0.09
     secret
    -0.09
     reb
    -0.09
     healing
    -0.09
     clandest
    -0.09
    POSITIVE LOGITS
     stranded
    0.22
     predic
    0.18
     hopeless
    0.17
     unlucky
    0.16
     helpless
    0.15
     panic
    0.15
     luck
    0.15
    Luckily
    0.15
     panicked
    0.14
     Luckily
    0.14
    Activations Density 0.051%

    No Known Activations