© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3477
    Prev
    Next
    INDEX
    Explanations

    thinks it's impossible

    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
    Negative Logits
     narration
    -0.11
    enha
    -0.09
    -h
    -0.09
     precaution
    -0.09
     narr
    -0.09
     tone
    -0.09
    -navigation
    -0.09
    262
    -0.09
     note
    -0.08
     suspicions
    -0.08
    POSITIVE LOGITS
     desn
    0.10
     Bryant
    0.10
     bast
    0.10
    ÑĢÑĭ
    0.09
     bbw
    0.09
     Phill
    0.09
    Ru
    0.09
    das
    0.08
     Bast
    0.08
    sex
    0.08
    Activations Density 0.330%

    No Known Activations