© 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. 8000
    Prev
    Next
    INDEX
    Explanations

    like

    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
     Burl
    -0.11
    affer
    -0.10
    ellan
    -0.10
     todd
    -0.10
    00
    -0.10
    374
    -0.10
    _outer
    -0.10
    onto
    -0.10
    ooter
    -0.09
    isz
    -0.09
    POSITIVE LOGITS
     like
    0.60
     Like
    0.48
    like
    0.45
    Like
    0.44
     LIKE
    0.43
    _like
    0.38
    -like
    0.38
    åĥı
    0.33
    .like
    0.32
     likes
    0.30
    Activations Density 0.286%

    No Known Activations