© 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. 92610
    Prev
    Next
    INDEX
    Explanations

    shit entirely

    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
    ed
    -0.12
    er
    -0.11
    eled
    -0.11
    erate
    -0.11
    es
    -0.11
    orate
    -0.11
    hair
    -0.11
    hic
    -0.11
    hoot
    -0.11
    ek
    -0.11
    POSITIVE LOGITS
     stains
    0.12
     stain
    0.12
    izens
    0.11
    ernals
    0.11
    TY
    0.11
    walker
    0.11
     happens
    0.11
    ting
    0.10
    TING
    0.10
    loads
    0.10
    Activations Density 0.004%

    No Known Activations