© 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. 87705
    Prev
    Next
    INDEX
    Explanations

    left, leave, leaves

    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
     chill
    -0.08
     decent
    -0.08
    uter
    -0.08
     symb
    -0.08
     javax
    -0.08
     sight
    -0.08
     mastering
    -0.08
    zel
    -0.08
     gaining
    -0.08
     sympathy
    -0.08
    POSITIVE LOGITS
     dripping
    0.11
    ãĥ³ãĤ°
    0.09
    awi
    0.09
     Taste
    0.09
    ZH
    0.09
     vulner
    0.09
    -nil
    0.09
    usz
    0.09
    ifa
    0.09
    ingu
    0.09
    Activations Density 0.001%

    No Known Activations