© 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. 87941
    Prev
    Next
    INDEX
    Explanations

    watching videos

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bru
    -0.09
    mailto
    -0.09
     mobility
    -0.09
     elong
    -0.09
     chemistry
    -0.08
     communic
    -0.08
     ect
    -0.08
     Bru
    -0.08
     wear
    -0.08
     flexibility
    -0.08
    POSITIVE LOGITS
     downloading
    0.23
     DVDs
    0.21
     pornography
    0.21
     porn
    0.21
     downloaded
    0.21
     viewing
    0.21
     DVD
    0.20
     downloads
    0.20
     Netflix
    0.19
     Watching
    0.18
    Activations Density 0.053%

    No Known Activations