© 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. 25245
    Prev
    Next
    INDEX
    Explanations

    directory listing submission

    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
     buc
    -0.10
     Netflix
    -0.09
     Constitutional
    -0.09
    /team
    -0.09
    /header
    -0.09
     Trustees
    -0.09
     recon
    -0.08
     Vaccine
    -0.08
    Netflix
    -0.08
    .Conv
    -0.08
    POSITIVE LOGITS
     directories
    0.24
     submission
    0.23
     directory
    0.23
     Submit
    0.22
     Directory
    0.22
     Submission
    0.22
    directory
    0.21
     listing
    0.21
     submit
    0.21
     submissions
    0.21
    Activations Density 0.338%

    No Known Activations