© 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. 8084
    Prev
    Next
    INDEX
    Explanations

    middle or interior 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
    Negative Logits
    ucken
    -0.12
     outnumber
    -0.11
     Mum
    -0.11
     nond
    -0.10
     extrav
    -0.10
     boarding
    -0.10
     Monday
    -0.09
    izar
    -0.09
     amet
    -0.09
     compliment
    -0.09
    POSITIVE LOGITS
     mid
    0.27
     middle
    0.26
     interior
    0.25
    middle
    0.22
     elsewhere
    0.22
    mid
    0.20
     midpoint
    0.19
     Interior
    0.19
     Mid
    0.19
     inland
    0.19
    Activations Density 0.360%

    No Known Activations