© 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. 46184
    Prev
    Next
    INDEX
    Explanations

    non-English characters and numbers

    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
    غ
    -0.09
    ét
    -0.09
     boss
    -0.09
    dek
    -0.08
    onen
    -0.08
     orm
    -0.08
     presumption
    -0.08
    Ø®
    -0.08
     Ca
    -0.08
    stre
    -0.08
    POSITIVE LOGITS
     вÑĢем
    0.10
    eled
    0.10
    bral
    0.10
    ifen
    0.10
    ichel
    0.09
    ews
    0.09
    ë£Į
    0.09
    ified
    0.09
    Zone
    0.09
    ily
    0.09
    Activations Density 0.005%

    No Known Activations