© 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. 46144
    Prev
    Next
    INDEX
    Explanations

    github, git, gpu

    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
    rust
    -0.14
     Rage
    -0.11
     unc
    -0.11
    aked
    -0.10
     twig
    -0.10
    acking
    -0.10
     grim
    -0.10
    cker
    -0.09
    ewe
    -0.09
    ikel
    -0.09
    POSITIVE LOGITS
    ëĬ¥
    0.11
    ileo
    0.10
    matic
    0.10
    vine
    0.10
    untlet
    0.10
    hound
    0.09
     pains
    0.09
    -grand
    0.09
    ging
    0.09
    nosis
    0.08
    Activations Density 0.001%

    No Known Activations