© 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. 87835
    Prev
    Next
    INDEX
    Explanations

    getting attention

    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
    agon
    -0.10
    uch
    -0.10
    akk
    -0.10
    lena
    -0.09
     proph
    -0.09
    dbl
    -0.09
    tha
    -0.09
    erah
    -0.08
     wid
    -0.08
     swings
    -0.08
    POSITIVE LOGITS
     attention
    0.41
     Attention
    0.38
    attention
    0.34
    Attention
    0.34
    _attention
    0.24
     attract
    0.24
     attracting
    0.23
     attracts
    0.22
     attent
    0.22
     interrupt
    0.20
    Activations Density 0.157%

    No Known Activations