© 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. 50834
    Prev
    Next
    INDEX
    Explanations

    your browser

    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
     [âĢ¦
    -0.10
    Rx
    -0.09
     terrace
    -0.09
    andel
    -0.09
    Pipe
    -0.08
     [âĢ¦]↵↵
    -0.08
     testimonials
    -0.08
     [âĢ¦]
    -0.08
    .âĢ¢
    -0.08
     trainable
    -0.08
    POSITIVE LOGITS
     Pants
    0.09
    pants
    0.09
     unintention
    0.08
     Offensive
    0.08
     obst
    0.08
    cke
    0.08
     Hen
    0.08
    nbr
    0.08
    _lazy
    0.08
     urb
    0.08
    Activations Density 0.018%

    No Known Activations