© 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. 87862
    Prev
    Next
    INDEX
    Explanations

    single tap or click

    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
     hele
    -0.09
     Entire
    -0.09
     Lump
    -0.09
     noticeably
    -0.08
     backed
    -0.08
     Hanson
    -0.08
     revived
    -0.08
     attempting
    -0.08
    IVE
    -0.08
     Platform
    -0.08
    POSITIVE LOGITS
     click
    0.25
     glance
    0.25
     swipe
    0.24
     flick
    0.24
     clicks
    0.20
     keyst
    0.19
     flip
    0.17
     press
    0.17
     blink
    0.17
    click
    0.17
    Activations Density 0.167%

    No Known Activations