© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27567
    Prev
    Next
    INDEX
    Explanations

    use only carefully

    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
    irim
    -0.11
    dek
    -0.10
    YM
    -0.09
     Crud
    -0.09
    '%
    -0.09
    ryn
    -0.09
     ostensibly
    -0.09
    oret
    -0.08
    usc
    -0.08
     perfectly
    -0.08
    POSITIVE LOGITS
     sparing
    0.33
     wisely
    0.30
     responsibly
    0.28
     cautiously
    0.27
     only
    0.27
     carefully
    0.26
     ONLY
    0.24
    spar
    0.23
     selectively
    0.22
     jud
    0.22
    Activations Density 0.444%

    No Known Activations