© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    iPad and tablets

    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
     Telephone
    -0.16
     telephone
    -0.15
    Telephone
    -0.14
     trunk
    -0.12
    telephone
    -0.12
     téléphone
    -0.12
     bottled
    -0.11
     hotline
    -0.11
     bott
    -0.11
     Telefon
    -0.10
    POSITIVE LOGITS
     tablet
    0.46
     Tablet
    0.41
     tablets
    0.41
     iPad
    0.38
     Tablets
    0.38
    tablet
    0.34
    iPad
    0.32
     ipad
    0.29
     touchscreen
    0.26
     iP
    0.26
    Activations Density 1.204%

    No Known Activations