© 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. 18478
    Prev
    Next
    INDEX
    Explanations

    locations and their attributes

    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
     tod
    -0.11
    yal
    -0.09
     Rural
    -0.09
    UNC
    -0.09
     bre
    -0.08
    PO
    -0.08
    -desc
    -0.08
     Islanders
    -0.08
     Tod
    -0.08
     Creed
    -0.08
    POSITIVE LOGITS
    /state
    0.14
    /world
    0.12
     capital
    0.12
     of
    0.12
    wide
    0.11
    _of
    0.11
    pire
    0.11
    pname
    0.10
    chan
    0.10
    ogan
    0.10
    Activations Density 0.235%

    No Known Activations