© 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. 8226
    Prev
    Next
    INDEX
    Explanations

    band members leaving

    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
     pole
    -0.13
    ITU
    -0.11
     Katherine
    -0.10
    jab
    -0.10
    ugu
    -0.10
     Dere
    -0.10
     Pole
    -0.10
     Cly
    -0.10
     aest
    -0.09
     Sanford
    -0.09
    POSITIVE LOGITS
     crack
    0.14
     Crack
    0.14
     cracks
    0.13
     lineup
    0.12
     cracking
    0.11
     Quit
    0.10
     similarities
    0.10
     roster
    0.10
     quitting
    0.10
     similarity
    0.10
    Activations Density 0.009%

    No Known Activations