© 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. 87984
    Prev
    Next
    INDEX
    Explanations

    contacted me

    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
    quisition
    -0.12
    inq
    -0.11
    .leading
    -0.11
     unl
    -0.10
     jig
    -0.10
    egl
    -0.10
     Zig
    -0.10
    etz
    -0.10
    isman
    -0.10
    iman
    -0.10
    POSITIVE LOGITS
     about
    0.11
     telling
    0.10
     personally
    0.09
     directly
    0.09
     fing
    0.09
     informing
    0.09
     regarding
    0.08
     posing
    0.08
     saying
    0.08
     privately
    0.08
    Activations Density 0.052%

    No Known Activations