© 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. 25065
    Prev
    Next
    INDEX
    Explanations

    Munro or Munoz

    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
    tright
    -0.10
    gles
    -0.10
    veis
    -0.10
     Attached
    -0.10
    uers
    -0.09
     shortest
    -0.09
    rg
    -0.09
     dy
    -0.09
     pel
    -0.09
     ãĥ»
    -0.09
    POSITIVE LOGITS
    itions
    0.13
    mun
    0.11
    itor
    0.11
    oz
    0.11
    ition
    0.10
    ificent
    0.10
    ster
    0.10
     mun
    0.09
    sters
    0.09
    qid
    0.09
    Activations Density 0.035%

    No Known Activations