© 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. 92344
    Prev
    Next
    INDEX
    Explanations

    West/East followed by location

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Pil
    -0.09
    orse
    -0.08
    thon
    -0.08
    ä¿Ŀ
    -0.07
    isko
    -0.07
     Slow
    -0.07
     bull
    -0.07
    -times
    -0.07
    uster
    -0.07
    pline
    -0.07
    POSITIVE LOGITS
    anh
    0.13
    ropp
    0.13
     Brooklyn
    0.12
    enders
    0.12
     OUTER
    0.12
    iali
    0.11
    lake
    0.11
    inis
    0.11
    bound
    0.11
    mont
    0.11
    Activations Density 0.038%

    No Known Activations