© 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. 92275
    Prev
    Next
    INDEX
    Explanations

    Natalia or antenatal

    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
     Sno
    -0.11
     punct
    -0.11
     Hust
    -0.10
     ras
    -0.10
     Vog
    -0.10
     nast
    -0.10
     elm
    -0.10
    QUIT
    -0.10
    glas
    -0.09
     everlasting
    -0.09
    POSITIVE LOGITS
     Kemp
    0.09
    olist
    0.08
    amine
    0.08
     recon
    0.07
    /block
    0.07
     enfer
    0.07
     pie
    0.07
    ackage
    0.07
     afterward
    0.07
     disgusted
    0.07
    Activations Density 0.005%

    No Known Activations