© 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. 29572
    Prev
    Next
    INDEX
    Explanations

    leave/left variants

    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
    ller
    -0.12
    ikon
    -0.11
     kne
    -0.10
    idot
    -0.10
     con
    -0.09
     sticky
    -0.09
     circulating
    -0.09
     Jarvis
    -0.09
     delt
    -0.09
     cones
    -0.09
    POSITIVE LOGITS
     aside
    0.12
     behind
    0.11
     Trou
    0.09
     afar
    0.08
    ONSE
    0.08
    è¿ij
    0.08
     away
    0.08
     maiden
    0.08
     ample
    0.08
     unforgettable
    0.08
    Activations Density 0.071%

    No Known Activations