© 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. 111395
    Prev
    Next
    INDEX
    Explanations

    important role or aspect

    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
    ivo
    -0.10
    esh
    -0.08
    urse
    -0.08
     versions
    -0.08
     Bout
    -0.08
    ivet
    -0.08
     globe
    -0.08
    DL
    -0.08
     fascinating
    -0.08
     rendition
    -0.08
    POSITIVE LOGITS
     aspect
    0.17
     step
    0.16
     role
    0.16
    /sign
    0.15
     consideration
    0.15
     factor
    0.14
     element
    0.14
     ingredient
    0.14
     milestone
    0.14
     Role
    0.13
    Activations Density 0.162%

    No Known Activations