© 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. 46165
    Prev
    Next
    INDEX
    Explanations

    non-

    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
     cleanly
    -0.12
     safely
    -0.11
     comfortably
    -0.10
    safe
    -0.10
     peacefully
    -0.10
    aday
    -0.10
    ighter
    -0.10
     stable
    -0.10
    ص
    -0.09
     vet
    -0.09
    POSITIVE LOGITS
     harmful
    0.15
     toxic
    0.12
     invasive
    0.11
     compromise
    0.11
     irritating
    0.11
     Toxic
    0.11
     hazardous
    0.10
     compromising
    0.10
     messy
    0.10
     harming
    0.10
    Activations Density 0.101%

    No Known Activations