© 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. 25152
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
     moot
    -0.12
     inadvertently
    -0.11
     inevitable
    -0.10
     somehow
    -0.10
     unavoid
    -0.10
     even
    -0.10
    zend
    -0.10
     innoc
    -0.10
     clums
    -0.09
    adel
    -0.09
    POSITIVE LOGITS
     called
    0.16
    称
    0.13
     Called
    0.12
    called
    0.12
    Called
    0.12
     termed
    0.11
     hired
    0.11
     nicknamed
    0.11
     wore
    0.09
     hire
    0.09
    Activations Density 0.025%

    No Known Activations