© 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. 46200
    Prev
    Next
    INDEX
    Explanations

    many / understanding / 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
     THEY
    -0.13
     they
    -0.11
     unlike
    -0.11
     They
    -0.11
     Voc
    -0.11
     he
    -0.10
     although
    -0.10
     Convenient
    -0.10
    sel
    -0.10
    oric
    -0.10
    POSITIVE LOGITS
     understandably
    0.12
     finding
    0.11
     shouldn
    0.11
     many
    0.11
     naturally
    0.10
     why
    0.10
     coupled
    0.10
     sometimes
    0.10
     unsur
    0.09
     understanding
    0.09
    Activations Density 0.301%

    No Known Activations